[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-TarrySingh--Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials":3,"tool-TarrySingh--Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials":61},[4,18,26,36,44,53],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",160411,2,"2026-04-18T23:33:24",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":32,"last_commit_at":42,"category_tags":43,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",109154,"2026-04-18T11:18:24",[14,15,13],{"id":45,"name":46,"github_repo":47,"description_zh":48,"stars":49,"difficulty_score":32,"last_commit_at":50,"category_tags":51,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[52,13,15,14],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":32,"last_commit_at":59,"category_tags":60,"status":17},4721,"markitdown","microsoft\u002Fmarkitdown","MarkItDown 是一款由微软 AutoGen 团队打造的轻量级 Python 工具，专为将各类文件高效转换为 Markdown 格式而设计。它支持 PDF、Word、Excel、PPT、图片（含 OCR）、音频（含语音转录）、HTML 乃至 YouTube 链接等多种格式的解析，能够精准提取文档中的标题、列表、表格和链接等关键结构信息。\n\n在人工智能应用日益普及的今天，大语言模型（LLM）虽擅长处理文本，却难以直接读取复杂的二进制办公文档。MarkItDown 恰好解决了这一痛点，它将非结构化或半结构化的文件转化为模型“原生理解”且 Token 效率极高的 Markdown 格式，成为连接本地文件与 AI 分析 pipeline 的理想桥梁。此外，它还提供了 MCP（模型上下文协议）服务器，可无缝集成到 Claude Desktop 等 LLM 应用中。\n\n这款工具特别适合开发者、数据科学家及 AI 研究人员使用，尤其是那些需要构建文档检索增强生成（RAG）系统、进行批量文本分析或希望让 AI 助手直接“阅读”本地文件的用户。虽然生成的内容也具备一定可读性，但其核心优势在于为机器",93400,"2026-04-06T19:52:38",[52,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":67,"readme_en":68,"readme_zh":69,"quickstart_zh":70,"use_case_zh":71,"hero_image_url":72,"owner_login":73,"owner_name":74,"owner_avatar_url":75,"owner_bio":76,"owner_company":77,"owner_location":78,"owner_email":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":119,"forks":120,"last_commit_at":121,"license":122,"difficulty_score":32,"env_os":123,"env_gpu":124,"env_ram":123,"env_deps":125,"category_tags":138,"github_topics":140,"view_count":32,"oss_zip_url":159,"oss_zip_packed_at":159,"status":17,"created_at":160,"updated_at":161,"faqs":162,"releases":163},9346,"TarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials","Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials","A comprehensive list of Deep Learning \u002F Artificial Intelligence and Machine Learning tutorials - rapidly expanding into areas of AI\u002FDeep Learning \u002F Machine Vision \u002F NLP and industry specific areas such as Climate \u002F Energy, Automotives, Retail, Pharma, Medicine, Healthcare, Policy, Ethics and more.","Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 是一个全面且持续更新的开源教程集合，旨在帮助学习者系统掌握深度学习、人工智能及机器学习的核心知识与实战技能。它汇集了从基础理论到行业应用的大量资源，覆盖计算机视觉、自然语言处理，以及气候能源、医疗健康、自动驾驶等垂直领域，有效解决了初学者难以寻找系统化学习路径、开发者缺乏行业落地案例参考的痛点。\n\n这份教程库特别适合 AI 开发者、数据科学家、研究人员以及希望转型进入 AI 领域的工程师使用。无论是想夯实 Python 数据分析基础（如 Pandas、NumPy），还是深入钻研 PyTorch、TensorFlow、Uber Pyro 等主流框架，都能在这里找到对应的 IPython Notebook 代码示例和详细指南。\n\n其独特亮点在于紧跟技术前沿，不仅包含传统的机器学习算法，还每日更新涉及 GPU 编程、以数据为中心的 AI（Data-Centric AI）以及 Web3 与可持续 AI 结合等新兴主题。所有教程均针对 NVIDIA GPU 环境进行了","Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 是一个全面且持续更新的开源教程集合，旨在帮助学习者系统掌握深度学习、人工智能及机器学习的核心知识与实战技能。它汇集了从基础理论到行业应用的大量资源，覆盖计算机视觉、自然语言处理，以及气候能源、医疗健康、自动驾驶等垂直领域，有效解决了初学者难以寻找系统化学习路径、开发者缺乏行业落地案例参考的痛点。\n\n这份教程库特别适合 AI 开发者、数据科学家、研究人员以及希望转型进入 AI 领域的工程师使用。无论是想夯实 Python 数据分析基础（如 Pandas、NumPy），还是深入钻研 PyTorch、TensorFlow、Uber Pyro 等主流框架，都能在这里找到对应的 IPython Notebook 代码示例和详细指南。\n\n其独特亮点在于紧跟技术前沿，不仅包含传统的机器学习算法，还每日更新涉及 GPU 编程、以数据为中心的 AI（Data-Centric AI）以及 Web3 与可持续 AI 结合等新兴主题。所有教程均针对 NVIDIA GPU 环境进行了优化加速，并提供了来自 Netflix、Uber 等科技巨头的实际项目案例。如果你渴望在实战中提升技能，或探索 AI 在特定行业的创新应用，这里将是你不可或缺的学习伴侣。","# NEW LIST 2023 - 2024: Machine-Learning \u002F Deep-Learning \u002F AI + Web3 -Tutorials\n\nHi - Thanks for dropping by!\u003Cbr>\n\u003Cbr>\nI will be updating this tutorials site on a \u003Cb>daily basis\u003C\u002Fb> adding all relevant topcis for 2022 - 2024 especially pertaining to **GPU programming, Data Centric AI, Emerging topics like Sustainable AI with Web3AI.js (DeFI, DAO, NFT) and much more**.\u003Cbr>\n\n**NOTE: All these tutorials are supported and accelerated on NVIDIA GPUs**\n\u003Cbr>\nMore importantly the applications of ML\u002FDL\u002FAI into industry areas such as Transportation, Medicine\u002FHealthcare etc. will be something I'll watch with keen interest and would love to share the same with you.\n\u003Cbr>\nFinally, it is **YOUR** help I will seek to make it more useful and less boring, so please do suggest\u002Fcomment\u002Fcontribute!\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_07e0d6db9002.png\">\n\u003C\u002Fp>\n\n## Index\n\n* [deep-learning](#deep-learning)\n   * [UBER | Pyro](#uber-pyro-probabalistic-tutorials)\n   * [Netflix | VectorFlow](#netflix-vectorflow-tutorials)\n   * [PyTorch](#pytorch-tutorials)\n   * [tensorflow](#tensor-flow-tutorials)\n   * [theano](#theano-tutorials)\n   * [keras](#keras-tutorials)\n   * [caffe](#deep-learning-misc)\n   * [Torch\u002FLua]()\n   * [MXNET]()\n   \n* [scikit-learn](#scikit-learn)\n* [statistical-inference-scipy](#statistical-inference-scipy)\n* [pandas](#pandas)\n* [matplotlib](#matplotlib)\n* [numpy](#numpy)\n* [python-data](#python-data)\n* [kaggle-and-business-analyses](#kaggle-and-business-analyses)\n* [spark](#spark)\n* [mapreduce-python](#mapreduce-python)\n* [amazon web services](#aws)\n* [command lines](#commands)\n* [misc](#misc)\n* [notebook-installation](#notebook-installation)\n* [Curated list of Deep Learning \u002F AI blogs](#curated-list-of-deeplearning-blogs)\n* [credits](#credits)\n* [contributing](#contributing)\n* [contact-info](#contact-info)\n* [license](#license)\n\n## deep-learning\n\nIPython Notebook(s) and other programming tools such as Torch\u002FLua\u002FD lang in demonstrating deep learning functionality.\n\n### uber-pyro-probabalistic-tutorials\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_2655e2ef08a7.png\">\n\u003C\u002Fp>\n\nAdditional PyRo tutorials:\n\n* [pyro-examples\u002Ffull examples](http:\u002F\u002Fpyro.ai\u002Fexamples\u002F)\n* [pyro-examples\u002FVariational Autoencoders](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fvae.html)\n* [pyro-examples\u002FBayesian Regression](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fbayesian_regression.html)\n* [pyro-examples\u002FDeep Markov Model](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fdmm.html)\n* [pyro-examples\u002FAIR(Attend Infer Repeat)](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fair.html)\n* [pyro-examples\u002FSemi-Supervised VE](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fss-vae.html)\n* [pyro-examples\u002FGMM](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fgmm.html)\n* [pyro-examples\u002FGaussian Process](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fgp.html)\n* [pyro-examples\u002FBayesian Optimization](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fbo.html)\n* [Full Pyro Code](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Ftree\u002Fmaster\u002Fdeep-learning\u002FUBER-pyro)\n\n\n\n### netflix-vectorflow-tutorials\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_efed42c2474b.png\">\n\u003C\u002Fp>\n\n* [MNIST Example, running with Dlang](https:\u002F\u002Fgithub.com\u002FNetflix\u002Fvectorflow\u002Ftree\u002Fmaster\u002Fexamples)\n\n### pytorch-tutorials\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_95e5cda72c5c.png\">\n\u003C\u002Fp>\n\n| Level | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Beginners\u002FZakizhou](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fbeginner_source) | Learning the basics of PyTorch from Facebook. |\n| [Intermedia\u002FQuanvuong](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fintermediate_source) | Learning the intermediate stuff about PyTorch of from Facebook. |\n| [Advanced\u002FChsasank](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fadvanced_source) | Learning the advanced stuff about PyTorch of from Facebook. |\n| [Learning PyTorch by Examples - Numpy, Tensors and Autograd](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Ftree\u002Fmaster\u002Fpytorch) | At its core, PyTorch provides two main features an n-dimensional Tensor, similar to numpy but can run on GPUs AND automatic differentiation for building and training neural networks. |\n| [PyTorch - Getting to know autograd.Variable, Gradient, Neural Network](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpytorch\u002FPyTorch%20NN%20Basics%20-%20Autograd%20Gradient%20Neural%20Network%20Loss%20Backprop.ipynb) | Here we start with ultimate basics of Tensors, wrap a Tensor with Variable module, play with nn.Module and implement forward and backward function. |\n\n\n### tensor-flow-tutorials\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_fef6d0bb0d1b.png\">\n\u003C\u002Fp>\nAdditional TensorFlow tutorials:\n\n* [pkmital\u002Ftensorflow_tutorials](https:\u002F\u002Fgithub.com\u002Fpkmital\u002Ftensorflow_tutorials)\n* [nlintz\u002FTensorFlow-Tutorials](https:\u002F\u002Fgithub.com\u002Fnlintz\u002FTensorFlow-Tutorials)\n* [alrojo\u002Ftensorflow-tutorial](https:\u002F\u002Fgithub.com\u002Falrojo\u002Ftensorflow-tutorial)\n* [BinRoot\u002FTensorFlow-Book](https:\u002F\u002Fgithub.com\u002FBinRoot\u002FTensorFlow-Book)\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tsf-basics](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F1_intro\u002Fbasic_operations.ipynb) | Learn basic operations in TensorFlow, a library for various kinds of perceptual and language understanding tasks from Google. |\n| [tsf-linear](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Flinear_regression.ipynb) | Implement linear regression in TensorFlow. |\n| [tsf-logistic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Flogistic_regression.ipynb) | Implement logistic regression in TensorFlow. |\n| [tsf-nn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Fnearest_neighbor.ipynb) | Implement nearest neighboars in TensorFlow. |\n| [tsf-alex](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Falexnet.ipynb) | Implement AlexNet in TensorFlow. |\n| [tsf-cnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Fconvolutional_network.ipynb) | Implement convolutional neural networks in TensorFlow. |\n| [tsf-mlp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Fmultilayer_perceptron.ipynb) | Implement multilayer perceptrons in TensorFlow. |\n| [tsf-rnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Frecurrent_network.ipynb) | Implement recurrent neural networks in TensorFlow. |\n| [tsf-gpu](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F4_multi_gpu\u002Fmultigpu_basics.ipynb) | Learn about basic multi-GPU computation in TensorFlow. |\n| [tsf-gviz](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F5_ui\u002Fgraph_visualization.ipynb) | Learn about graph visualization in TensorFlow. |\n| [tsf-lviz](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F5_ui\u002Floss_visualization.ipynb) | Learn about loss visualization in TensorFlow. |\n\n### tensor-flow-exercises\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tsf-not-mnist](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F1_notmnist.ipynb) | Learn simple data curation by creating a pickle with formatted datasets for training, development and testing in TensorFlow. |\n| [tsf-fully-connected](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F2_fullyconnected.ipynb) | Progressively train deeper and more accurate models using logistic regression and neural networks in TensorFlow. |\n| [tsf-regularization](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F3_regularization.ipynb) | Explore regularization techniques by training fully connected networks to classify notMNIST characters in TensorFlow. |\n| [tsf-convolutions](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F4_convolutions.ipynb) | Create convolutional neural networks in TensorFlow. |\n| [tsf-word2vec](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F5_word2vec.ipynb) | Train a skip-gram model over Text8 data in TensorFlow. |\n| [tsf-lstm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F6_lstm.ipynb) | Train a LSTM character model over Text8 data in TensorFlow. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"http:\u002F\u002Fwww.deeplearning.net\u002Fsoftware\u002Ftheano\u002F_static\u002Ftheano_logo_allblue_200x46.png\">\n\u003C\u002Fp>\n\n### theano-tutorials\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [theano-intro](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fintro_theano\u002Fintro_theano.ipynb) | Intro to Theano, which allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation. |\n| [theano-scan](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fscan_tutorial\u002Fscan_tutorial.ipynb) | Learn scans, a mechanism to perform loops in a Theano graph. |\n| [theano-logistic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fintro_theano\u002Flogistic_regression.ipynb) | Implement logistic regression in Theano. |\n| [theano-rnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Frnn_tutorial\u002Fsimple_rnn.ipynb) | Implement recurrent neural networks in Theano. |\n| [theano-mlp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Ftheano_mlp\u002Ftheano_mlp.ipynb) | Implement multilayer perceptrons in Theano. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"http:\u002F\u002Fi.imgur.com\u002FL45Q8c2.jpg\">\n\u003C\u002Fp>\n\n### keras-tutorials\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| keras | Keras is an open source neural network library written in Python. It is capable of running on top of either Tensorflow or Theano. |\n| [setup](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002FREADME.md) | Learn about the tutorial goals and how to set up your Keras environment. |\n| [intro-deep-learning-ann](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1%20Introduction%20-%20Deep%20Learning%20and%20ANN.ipynb) | Get an intro to deep learning with Keras and Artificial Neural Networks (ANN). |\n| [Perceptrons and Adaline](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1.1%20Perceptron%20and%20Adaline.ipynb) | Implement Peceptron and adaptive linear neurons. |\n| [MLP and MNIST Data](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1.2%20MLP%20and%20MNIST.ipynb) | Classifying handwritten digits,implement MLP, train and debug ANN |\n| [theano](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.2%20Introduction%20-%20Theano.ipynb) | Learn about Theano by working with weights matrices and gradients. |\n| [keras-otto](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.3%20Introduction%20-%20Keras.ipynb) | Learn about Keras by looking at the Kaggle Otto challenge. |\n| [ann-mnist](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.4%20(Extra)%20A%20Simple%20Implementation%20of%20ANN%20for%20MNIST.ipynb) | Review a simple implementation of ANN for MNIST using Keras. |\n| [conv-nets](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.1%20Supervised%20Learning%20-%20ConvNets.ipynb) | Learn about Convolutional Neural Networks (CNNs) with Keras. |\n| [conv-net-1](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.2.1%20Supervised%20Learning%20-%20ConvNet%20HandsOn%20Part%20I.ipynb) | Recognize handwritten digits from MNIST using Keras - Part 1. |\n| [conv-net-2](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.2.2%20Supervised%20Learning%20-%20ConvNet%20HandsOn%20Part%20II.ipynb) | Recognize handwritten digits from MNIST using Keras - Part 2. |\n| [keras-models](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.3%20Supervised%20Learning%20-%20Famous%20Models%20with%20Keras.ipynb) | Use pre-trained models such as VGG16, VGG19, ResNet50, and Inception v3 with Keras. |\n| [auto-encoders](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F6.%20AutoEncoders%20and%20Embeddings\u002F6.1.%20AutoEncoders%20and%20Embeddings.ipynb) | Learn about Autoencoders with Keras. |\n| [rnn-lstm](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F7.%20Recurrent%20Neural%20Networks\u002F7.1%20RNN%20and%20LSTM.ipynb) | Learn about Recurrent Neural Networks (RNNs) with Keras. |\n| [lstm-sentence-gen](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F7.%20Recurrent%20Neural%20Networks\u002F7.2%20LSTM%20for%20Sentence%20Generation.ipynb) |  Learn about RNNs using Long Short Term Memory (LSTM) networks with Keras. |\n| [nlp-deep-learning](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F6.%20AutoEncoders%20and%20Embeddings\u002F6.2%20NLP%20and%20Deep%20Learning.ipynb) | Learn about NLP using ANN (Artificial Neural Networks. |\n| [hyperparamter-tuning](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F5.%20HyperParameter%20Tuning%20and%20Transfer%20Learning\u002F5.1%20HyperParameter%20Tuning.ipynb) | Hyperparamters tuning using keras-wrapper.scikit-learn |\n\n### deep-learning-misc\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [deep-dream](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Fdeep-dream\u002Fdream.ipynb) | Caffe-based computer vision program which uses a convolutional neural network to find and enhance patterns in images. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_1f65a7d5139b.png\">\n\u003C\u002Fp>\n\n## scikit-learn\n\nIPython Notebook(s) demonstrating scikit-learn functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [intro](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-intro.ipynb) | Intro notebook to scikit-learn.  Scikit-learn adds Python support for large, multi-dimensional arrays and matrices, along with a large library of high-level mathematical functions to operate on these arrays. |\n| [knn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-intro.ipynb#K-Nearest-Neighbors-Classifier) | Implement k-nearest neighbors in scikit-learn. |\n| [linear-reg](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-linear-reg.ipynb) | Implement linear regression in scikit-learn. |\n| [svm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-svm.ipynb) | Implement support vector machine classifiers with and without kernels in scikit-learn. |\n| [random-forest](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-random-forest.ipynb) | Implement random forest classifiers and regressors in scikit-learn. |\n| [k-means](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-k-means.ipynb) | Implement k-means clustering in scikit-learn. |\n| [pca](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-pca.ipynb) | Implement principal component analysis in scikit-learn. |\n| [gmm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-gmm.ipynb) | Implement Gaussian mixture models in scikit-learn. |\n| [validation](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-validation.ipynb) | Implement validation and model selection in scikit-learn. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_41fa0e3dc800.png\">\n\u003C\u002Fp>\n\n## statistical-inference-scipy\n\nIPython Notebook(s) demonstrating statistical inference with SciPy functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| scipy | SciPy is a collection of mathematical algorithms and convenience functions built on the Numpy extension of Python. It adds significant power to the interactive Python session by providing the user with high-level commands and classes for manipulating and visualizing data. |\n| [effect-size](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Feffect_size.ipynb) | Explore statistics that quantify effect size by analyzing the difference in height between men and women.  Uses data from the Behavioral Risk Factor Surveillance System (BRFSS) to estimate the mean and standard deviation of height for adult women and men in the United States. |\n| [sampling](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Fsampling.ipynb) | Explore random sampling by analyzing the average weight of men and women in the United States using BRFSS data. |\n| [hypothesis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Fhypothesis.ipynb) | Explore hypothesis testing by analyzing the difference of first-born babies compared with others. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_7ecca73c3570.png\">\n\u003C\u002Fp>\n\n## pandas\n\nIPython Notebook(s) demonstrating pandas functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [pandas](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002Fpandas.ipynb) | Software library written for data manipulation and analysis in Python. Offers data structures and operations for manipulating numerical tables and time series. |\n| [github-data-wrangling](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fviz\u002Fblob\u002Fmaster\u002Fgithubstats\u002Fdata_wrangling.ipynb) | Learn how to load, clean, merge, and feature engineer by analyzing GitHub data from the [`Viz`](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fviz) repo. |\n| [Introduction-to-Pandas](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.00-Introduction-to-Pandas.ipynb) | Introduction to Pandas. |\n| [Introducing-Pandas-Objects](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.01-Introducing-Pandas-Objects.ipynb) | Learn about Pandas objects. |\n| [Data Indexing and Selection](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.02-Data-Indexing-and-Selection.ipynb) | Learn about data indexing and selection in Pandas. |\n| [Operations-in-Pandas](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.03-Operations-in-Pandas.ipynb) | Learn about operating on data in Pandas. |\n| [Missing-Values](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.04-Missing-Values.ipynb) | Learn about handling missing data in Pandas. |\n| [Hierarchical-Indexing](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.05-Hierarchical-Indexing.ipynb) | Learn about hierarchical indexing in Pandas. |\n| [Concat-And-Append](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.06-Concat-And-Append.ipynb) | Learn about combining datasets: concat and append in Pandas. |\n| [Merge-and-Join](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.07-Merge-and-Join.ipynb) | Learn about combining datasets: merge and join in Pandas. |\n| [Aggregation-and-Grouping](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.08-Aggregation-and-Grouping.ipynb) | Learn about aggregation and grouping in Pandas. |\n| [Pivot-Tables](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.09-Pivot-Tables.ipynb) | Learn about pivot tables in Pandas. |\n| [Working-With-Strings](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.10-Working-With-Strings.ipynb) | Learn about vectorized string operations in Pandas. |\n| [Working-with-Time-Series](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.11-Working-with-Time-Series.ipynb) | Learn about working with time series in pandas. |\n| [Performance-Eval-and-Query](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.12-Performance-Eval-and-Query.ipynb) | Learn about high-performance Pandas: eval() and query() in Pandas. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_1f733496b99a.png\">\n\u003C\u002Fp>\n\n## matplotlib\n\nIPython Notebook(s) demonstrating matplotlib functionality.\n\n| Notebook | Description |\n|-----------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [matplotlib](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002Fmatplotlib.ipynb) | Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms. |\n| [matplotlib-applied](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002Fmatplotlib-applied.ipynb) | Apply matplotlib visualizations to Kaggle competitions for exploratory data analysis.  Learn how to create bar plots, histograms, subplot2grid, normalized plots, scatter plots, subplots, and kernel density estimation plots. |\n| [Introduction-To-Matplotlib](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.00-Introduction-To-Matplotlib.ipynb) | Introduction to Matplotlib. |\n| [Simple-Line-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.01-Simple-Line-Plots.ipynb) | Learn about simple line plots in Matplotlib. |\n| [Simple-Scatter-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.02-Simple-Scatter-Plots.ipynb) | Learn about simple scatter plots in Matplotlib. |\n| [Errorbars.ipynb](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.03-Errorbars.ipynb) | Learn about visualizing errors in Matplotlib. |\n| [Density-and-Contour-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.04-Density-and-Contour-Plots.ipynb) | Learn about density and contour plots in Matplotlib. |\n| [Histograms-and-Binnings](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.05-Histograms-and-Binnings.ipynb) | Learn about histograms, binnings, and density in Matplotlib. |\n| [Customizing-Legends](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.06-Customizing-Legends.ipynb) | Learn about customizing plot legends in Matplotlib. |\n| [Customizing-Colorbars](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.07-Customizing-Colorbars.ipynb) | Learn about customizing colorbars in Matplotlib. |\n| [Multiple-Subplots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.08-Multiple-Subplots.ipynb) | Learn about multiple subplots in Matplotlib. |\n| [Text-and-Annotation](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.09-Text-and-Annotation.ipynb) | Learn about text and annotation in Matplotlib. |\n| [Customizing-Ticks](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.10-Customizing-Ticks.ipynb) | Learn about customizing ticks in Matplotlib. |\n| [Settings-and-Stylesheets](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.11-Settings-and-Stylesheets.ipynb) | Learn about customizing Matplotlib: configurations and stylesheets. |\n| [Three-Dimensional-Plotting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.12-Three-Dimensional-Plotting.ipynb) | Learn about three-dimensional plotting in Matplotlib. |\n| [Geographic-Data-With-Basemap](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.13-Geographic-Data-With-Basemap.ipynb) | Learn about geographic data with basemap in Matplotlib. |\n| [Visualization-With-Seaborn](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.14-Visualization-With-Seaborn.ipynb) | Learn about visualization with Seaborn. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_d8b18f24aab6.png\">\n\u003C\u002Fp>\n\n## numpy\n\nIPython Notebook(s) demonstrating NumPy functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [numpy](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002Fnumpy.ipynb) | Adds Python support for large, multi-dimensional arrays and matrices, along with a large library of high-level mathematical functions to operate on these arrays. |\n| [Introduction-to-NumPy](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.00-Introduction-to-NumPy.ipynb) | Introduction to NumPy. |\n| [Understanding-Data-Types](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.01-Understanding-Data-Types.ipynb) | Learn about data types in Python. |\n| [The-Basics-Of-NumPy-Arrays](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.02-The-Basics-Of-NumPy-Arrays.ipynb) | Learn about the basics of NumPy arrays. |\n| [Computation-on-arrays-ufuncs](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.03-Computation-on-arrays-ufuncs.ipynb) | Learn about computations on NumPy arrays: universal functions. |\n| [Computation-on-arrays-aggregates](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.04-Computation-on-arrays-aggregates.ipynb) | Learn about aggregations: min, max, and everything in between in NumPy. |\n| [Computation-on-arrays-broadcasting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.05-Computation-on-arrays-broadcasting.ipynb) | Learn about computation on arrays: broadcasting in NumPy. |\n| [Boolean-Arrays-and-Masks](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.06-Boolean-Arrays-and-Masks.ipynb) | Learn about comparisons, masks, and boolean logic in NumPy. |\n| [Fancy-Indexing](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.07-Fancy-Indexing.ipynb) | Learn about fancy indexing in NumPy. |\n| [Sorting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.08-Sorting.ipynb) | Learn about sorting arrays in NumPy. |\n| [Structured-Data-NumPy](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.09-Structured-Data-NumPy.ipynb) | Learn about structured data: NumPy's structured arrays. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_50e2d1f52270.png\">\n\u003C\u002Fp>\n\n## python-data\n\nIPython Notebook(s) demonstrating Python functionality geared towards data analysis.\n\n| Notebook | Description |\n|-----------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------|\n| [data structures](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fstructs.ipynb) | Learn Python basics with tuples, lists, dicts, sets. |\n| [data structure utilities](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fstructs_utils.ipynb) | Learn Python operations such as slice, range, xrange, bisect, sort, sorted, reversed, enumerate, zip, list comprehensions. |\n| [functions](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Ffunctions.ipynb) | Learn about more advanced Python features: Functions as objects, lambda functions, closures, *args, **kwargs currying, generators, generator expressions, itertools. |\n| [datetime](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fdatetime.ipynb) | Learn how to work with Python dates and times: datetime, strftime, strptime, timedelta. |\n| [logging](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Flogs.ipynb) | Learn about Python logging with RotatingFileHandler and TimedRotatingFileHandler. |\n| [pdb](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fpdb.ipynb) | Learn how to debug in Python with the interactive source code debugger. |\n| [unit tests](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Funit_tests.ipynb) | Learn how to test in Python with Nose unit tests. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_a5a8d34c2278.png\">\n\u003C\u002Fp>\n\n## kaggle-and-business-analyses\n\nIPython Notebook(s) used in [kaggle](https:\u002F\u002Fwww.kaggle.com\u002F) competitions and business analyses.\n\n| Notebook | Description |\n|-------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|\n| [titanic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fkaggle\u002Ftitanic.ipynb) | Predict survival on the Titanic.  Learn data cleaning, exploratory data analysis, and machine learning. |\n| [churn-analysis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fanalyses\u002Fchurn.ipynb) | Predict customer churn.  Exercise logistic regression, gradient boosting classifers, support vector machines, random forests, and k-nearest-neighbors.  Includes discussions of confusion matrices, ROC plots, feature importances, prediction probabilities, and calibration\u002Fdescrimination.|\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_9be6a5e17d4e.png\">\n\u003C\u002Fp>\n\n## spark\n\nIPython Notebook(s) demonstrating spark and HDFS functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|\n| [spark](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fspark\u002Fspark.ipynb) | In-memory cluster computing framework, up to 100 times faster for certain applications and is well suited for machine learning algorithms. |\n| [hdfs](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fspark\u002Fhdfs.ipynb) | Reliably stores very large files across machines in a large cluster. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_51a67b8f1e2c.png\">\n\u003C\u002Fp>\n\n## mapreduce-python\n\nIPython Notebook(s) demonstrating Hadoop MapReduce with mrjob functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|\n| [mapreduce-python](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmapreduce\u002Fmapreduce-python.ipynb) | Runs MapReduce jobs in Python, executing jobs locally or on Hadoop clusters. Demonstrates Hadoop Streaming in Python code with unit test and [mrjob](https:\u002F\u002Fgithub.com\u002FYelp\u002Fmrjob) config file to analyze Amazon S3 bucket logs on Elastic MapReduce.  [Disco](https:\u002F\u002Fgithub.com\u002Fdiscoproject\u002Fdisco\u002F) is another python-based alternative.|\n\n\u003Cbr\u002F>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_75eb0ecb9a37.png\">\n\u003C\u002Fp>\n\n## aws\n\nIPython Notebook(s) demonstrating Amazon Web Services (AWS) and AWS tools functionality.\n\n\nAlso check out:\n\n* [SAWS](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fsaws): A Supercharged AWS command line interface (CLI).\n* [Awesome AWS](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fawesome-aws): A curated list of libraries, open source repos, guides, blogs, and other resources.\n\n| Notebook | Description |\n|------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [boto](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#Boto) | Official AWS SDK for Python. |\n| [s3cmd](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3cmd) | Interacts with S3 through the command line. |\n| [s3distcp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3distcp) | Combines smaller files and aggregates them together by taking in a pattern and target file.  S3DistCp can also be used to transfer large volumes of data from S3 to your Hadoop cluster. |\n| [s3-parallel-put](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3-parallel-put) | Uploads multiple files to S3 in parallel. |\n| [redshift](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#redshift) | Acts as a fast data warehouse built on top of technology from massive parallel processing (MPP). |\n| [kinesis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#kinesis) | Streams data in real time with the ability to process thousands of data streams per second. |\n| [lambda](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#lambda) | Runs code in response to events, automatically managing compute resources. |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_ab202643a12e.png\">\n\u003C\u002Fp>\n\n## commands\n\nIPython Notebook(s) demonstrating various command lines for Linux, Git, etc.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [linux](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Flinux.ipynb) | Unix-like and mostly POSIX-compliant computer operating system.  Disk usage, splitting files, grep, sed, curl, viewing running processes, terminal syntax highlighting, and Vim.|\n| [anaconda](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#anaconda) | Distribution of the Python programming language for large-scale data processing, predictive analytics, and scientific computing, that aims to simplify package management and deployment. |\n| [ipython notebook](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#ipython-notebook) | Web-based interactive computational environment where you can combine code execution, text, mathematics, plots and rich media into a single document. |\n| [git](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#git) | Distributed revision control system with an emphasis on speed, data integrity, and support for distributed, non-linear workflows. |\n| [ruby](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#ruby) | Used to interact with the AWS command line and for Jekyll, a blog framework that can be hosted on GitHub Pages. |\n| [jekyll](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#jekyll) | Simple, blog-aware, static site generator for personal, project, or organization sites.  Renders Markdown or Textile and Liquid templates, and produces a complete, static website ready to be served by Apache HTTP Server, Nginx or another web server. |\n| [pelican](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#pelican) | Python-based alternative to Jekyll. |\n| [django](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#django) | High-level Python Web framework that encourages rapid development and clean, pragmatic design. It can be useful to share reports\u002Fanalyses and for blogging. Lighter-weight alternatives include [Pyramid](https:\u002F\u002Fgithub.com\u002FPylons\u002Fpyramid), [Flask](https:\u002F\u002Fgithub.com\u002Fpallets\u002Fflask), [Tornado](https:\u002F\u002Fgithub.com\u002Ftornadoweb\u002Ftornado), and [Bottle](https:\u002F\u002Fgithub.com\u002Fbottlepy\u002Fbottle).\n\n## misc\n\nIPython Notebook(s) demonstrating miscellaneous functionality.\n\n| Notebook | Description |\n|--------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [regex](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmisc\u002Fregex.ipynb) | Regular expression cheat sheet useful in data wrangling.|\n[algorithmia](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmisc\u002FAlgorithmia.ipynb) | Algorithmia is a marketplace for algorithms. This notebook showcases 4 different algorithms: Face Detection, Content Summarizer, Latent Dirichlet Allocation and Optical Character Recognition.|\n\n## notebook-installation\n\n### anaconda\n\nAnaconda is a free distribution of the Python programming language for large-scale data processing, predictive analytics, and scientific computing that aims to simplify package management and deployment.\n\nFollow instructions to install [Anaconda](https:\u002F\u002Fdocs.continuum.io\u002Fanaconda\u002Finstall) or the more lightweight [miniconda](http:\u002F\u002Fconda.pydata.org\u002Fminiconda.html).\n\n### dev-setup\n\nFor detailed instructions, scripts, and tools to set up your development environment for data analysis, check out the [dev-setup](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fdev-setup) repo.\n\n### running-notebooks\n\nNote: If you intend to learn the hard way (preferred method)then I'd strongly advice to write as much code as you can yourself and not just run pre-written code. If you still want to test it, then do the following: \n\nTo view interactive content or to modify elements within the IPython notebooks, you must first clone or download the repository then run the notebook.  More information on IPython Notebooks can be found [here.](http:\u002F\u002Fipython.org\u002Fnotebook.html)\n\n    $ git clone https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials.git\n    $ cd Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\n    $ jupyter notebook\n    \n\nNotebooks tested with Python 3.7+\n\n## curated-list-of-deeplearning-blogs\n\n* A Blog From a Human-engineer-being http:\u002F\u002Fwww.erogol.com\u002F [(RSS)](http:\u002F\u002Fwww.erogol.com\u002Ffeed\u002F)\n* Aakash Japi http:\u002F\u002Faakashjapi.com\u002F [(RSS)](http:\u002F\u002Flogicx24.github.io\u002Ffeed.xml)\n* Adit Deshpande https:\u002F\u002Fadeshpande3.github.io\u002F [(RSS)](https:\u002F\u002Fadeshpande3.github.io\u002Fadeshpande3.github.io\u002Ffeed.xml)\n* Advanced Analytics & R http:\u002F\u002Fadvanceddataanalytics.net\u002F [(RSS)](http:\u002F\u002Fadvanceddataanalytics.net\u002Ffeed\u002F)\n* Adventures in Data Land http:\u002F\u002Fblog.smola.org [(RSS)](http:\u002F\u002Fblog.smola.org\u002Frss)\n* Agile Data Science http:\u002F\u002Fblog.sense.io\u002F [(RSS)](http:\u002F\u002Fblog.sense.io\u002Frss\u002F)\n* Ahmed El Deeb https:\u002F\u002Fmedium.com\u002F@D33B [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@D33B)\n* Airbnb Data blog http:\u002F\u002Fnerds.airbnb.com\u002Fdata\u002F [(RSS)](http:\u002F\u002Fnerds.airbnb.com\u002Ffeed\u002F)\n* Alex Castrounis | InnoArchiTech http:\u002F\u002Fwww.innoarchitech.com\u002F [(RSS)](http:\u002F\u002Fwww.innoarchitech.com\u002Ffeed.xml)\n* Alex Perrier http:\u002F\u002Falexperrier.github.io\u002F [(RSS)](http:\u002F\u002Falexperrier.github.io\u002Ffeed.xml)\n* Algobeans | Data Analytics Tutorials & Experiments for the Layman https:\u002F\u002Falgobeans.com [(RSS)](https:\u002F\u002Falgobeans.com\u002Ffeed\u002F)\n* Amazon AWS AI Blog https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fai\u002F [(RSS)](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Famazon-ai\u002Ffeed\u002F)\n* Analytics Vidhya http:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FAnalyticsVidhya)\n* Analytics and Visualization in Big Data @ Sicara https:\u002F\u002Fblog.sicara.com [(RSS)](https:\u002F\u002Fblog.sicara.com\u002Ffeed)\n* Andreas Müller http:\u002F\u002Fpeekaboo-vision.blogspot.com\u002F [(RSS)](http:\u002F\u002Fpeekaboo-vision.blogspot.com\u002Fatom.xml)\n* Andrej Karpathy blog http:\u002F\u002Fkarpathy.github.io\u002F [(RSS)](http:\u002F\u002Fkarpathy.github.io\u002Ffeed.xml)\n* Andrew Brooks http:\u002F\u002Fbrooksandrew.github.io\u002Fsimpleblog\u002F [(RSS)](http:\u002F\u002Fbrooksandrew.github.io\u002Fsimpleblog\u002Ffeed.xml)\n* Andrey Kurenkov http:\u002F\u002Fwww.andreykurenkov.com\u002Fwriting\u002F [(RSS)](http:\u002F\u002Fwww.andreykurenkov.com\u002Fwriting\u002Ffeed.xml\u002F)\n* Anton Lebedevich's Blog http:\u002F\u002Fmabrek.github.io\u002F [(RSS)](http:\u002F\u002Fmabrek.github.io\u002Ffeed.xml)\n* Arthur Juliani https:\u002F\u002Fmedium.com\u002F@awjuliani [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@awjuliani)\n* Audun M. Øygard http:\u002F\u002Fwww.auduno.com\u002F [(RSS)](http:\u002F\u002Fauduno.tumblr.com\u002Frss)\n* Avi Singh https:\u002F\u002Favisingh599.github.io\u002F [(RSS)](http:\u002F\u002Favisingh599.github.io\u002Ffeed.xml)\n* Beautiful Data http:\u002F\u002Fbeautifuldata.net\u002F [(RSS)](http:\u002F\u002Fbeautifuldata.net\u002Ffeed\u002F)\n* Beckerfuffle http:\u002F\u002Fmdbecker.github.io\u002F [(RSS)](http:\u002F\u002Fmdbecker.github.io\u002Fatom.xml)\n* Becoming A Data Scientist http:\u002F\u002Fwww.becomingadatascientist.com\u002F [(RSS)](http:\u002F\u002Fwww.becomingadatascientist.com\u002Ffeed\u002F)\n* Ben Bolte's Blog http:\u002F\u002Fbenjaminbolte.com\u002Fml\u002F [(RSS)](http:\u002F\u002Fbenjaminbolte.com\u002Fml\u002F)\n* Ben Frederickson http:\u002F\u002Fwww.benfrederickson.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.benfrederickson.com\u002Fatom.xml)\n* Berkeley AI Research http:\u002F\u002Fbair.berkeley.edu\u002Fblog\u002F [(RSS)](http:\u002F\u002Fbair.berkeley.edu\u002Fblog\u002Ffeed.xml)\n* Big-Ish Data http:\u002F\u002Fbigishdata.com\u002F [(RSS)](http:\u002F\u002Fbigishdata.com\u002Ffeed\u002F)\n* Blog on neural networks http:\u002F\u002Fyerevann.github.io\u002F [(RSS)](http:\u002F\u002Fyerevann.github.io\u002Fatom.xml)\n* Blogistic RegressionAbout Projects http:\u002F\u002Fd10genes.github.io\u002Fblog\u002F [(RSS)](http:\u002F\u002Fd10genes.github.io\u002Fblog\u002Ffeed.xml)\n* blogR | R tips and tricks from a scientist https:\u002F\u002Fdrsimonj.svbtle.com\u002F [(RSS)](https:\u002F\u002Fdrsimonj.svbtle.com\u002F)\n* Brain of mat kelcey http:\u002F\u002Fmatpalm.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmatpalm.com\u002Fblog\u002Ffeed)\n* Brilliantly wrong thoughts on science and programming https:\u002F\u002Farogozhnikov.github.io\u002F [(RSS)](http:\u002F\u002Farogozhnikov.github.io\u002Ffeed.xml)\n* Bugra Akyildiz http:\u002F\u002Fbugra.github.io\u002F [(RSS)](http:\u002F\u002Fbugra.github.io\u002Ffeeds\u002Fall.atom.xml)\n* Building Babylon https:\u002F\u002Fbuilding-babylon.net\u002F [(RSS)](http:\u002F\u002Fbuilding-babylon.net\u002Ffeed\u002F)\n* Carl Shan http:\u002F\u002Fcarlshan.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fcarlshan)\n* Chris Stucchio https:\u002F\u002Fwww.chrisstucchio.com\u002Fblog\u002Findex.html [(RSS)](http:\u002F\u002Fwww.chrisstucchio.com\u002Fblog\u002Fatom.xml)\n* Christophe Bourguignat https:\u002F\u002Fmedium.com\u002F@chris_bour [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@chris_bour)\n* Christopher Nguyen https:\u002F\u002Fmedium.com\u002F@ctn [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@ctn)\n* Cloudera Data Science Posts http:\u002F\u002Fblog.cloudera.com\u002Fblog\u002Fcategory\u002Fdata-science\u002F [(RSS)](http:\u002F\u002Fblog.cloudera.com\u002Fblog\u002Fcategory\u002Fdata-science\u002Ffeed\u002F)\n* colah's blog http:\u002F\u002Fcolah.github.io\u002Farchive.html [(RSS)](http:\u002F\u002Fcolah.github.io\u002Frss.xml)\n* Cortana Intelligence and Machine Learning Blog https:\u002F\u002Fblogs.technet.microsoft.com\u002Fmachinelearning\u002F [(RSS)](http:\u002F\u002Fblogs.technet.com\u002Fb\u002Fmachinelearning\u002Frss.aspx)\n* Daniel Forsyth http:\u002F\u002Fwww.danielforsyth.me\u002F [(RSS)](http:\u002F\u002Fwww.danielforsyth.me\u002Frss\u002F)\n* Daniel Homola http:\u002F\u002Fdanielhomola.com\u002Fcategory\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdanielhomola.com\u002Ffeed\u002F)\n* Daniel Nee http:\u002F\u002Fdanielnee.com [(RSS)](http:\u002F\u002Fdanielnee.com\u002F?feed=rss2)\n* Data Based Inventions http:\u002F\u002Fdatalab.lu\u002F [(RSS)](http:\u002F\u002Fdatalab.lu\u002Fatom.xml)\n* Data Blogger https:\u002F\u002Fwww.data-blogger.com\u002F [(RSS)](https:\u002F\u002Fwww.data-blogger.com\u002Ffeed\u002F)\n* Data Labs http:\u002F\u002Fblog.insightdatalabs.com\u002F [(RSS)](http:\u002F\u002Fblog.insightdatalabs.com\u002Frss\u002F)\n* Data Meets Media http:\u002F\u002Fdatameetsmedia.com\u002F [(RSS)](http:\u002F\u002Fdatameetsmedia.com\u002Ffeed\u002F)\n* Data Miners Blog http:\u002F\u002Fblog.data-miners.com\u002F [(RSS)](http:\u002F\u002Fblog.data-miners.com\u002Ffeeds\u002Fposts\u002Fdefault?alt=rss)\n* Data Mining Research http:\u002F\u002Fwww.dataminingblog.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fdataminingblog)\n* Data Mining: Text Mining, Visualization and Social Media http:\u002F\u002Fdatamining.typepad.com\u002Fdata_mining\u002F [(RSS)](http:\u002F\u002Fdatamining.typepad.com\u002Fdata_mining\u002Fatom.xml)\n* Data Piques http:\u002F\u002Fblog.ethanrosenthal.com\u002F [(RSS)](http:\u002F\u002Fblog.ethanrosenthal.com\u002Ffeeds\u002Fall.atom.xml)\n* Data School http:\u002F\u002Fwww.dataschool.io\u002F [(RSS)](http:\u002F\u002Fwww.dataschool.io\u002Frss\u002F)\n* Data Science 101 http:\u002F\u002F101.datascience.community\u002F [(RSS)](http:\u002F\u002F101.datascience.community\u002Ffeed\u002F)\n* Data Science @ Facebook https:\u002F\u002Fresearch.facebook.com\u002Fblog\u002Fdatascience\u002F [(RSS)](https:\u002F\u002Fresearch.facebook.com\u002Fblog\u002Fdatascience\u002F)\n* Data Science Insights http:\u002F\u002Fwww.datasciencebowl.com\u002Fdata-science-insights\u002F [(RSS)](http:\u002F\u002Fwww.datasciencebowl.com\u002Ffeed\u002F)\n* Data Science Tutorials https:\u002F\u002Fcodementor.io\u002Fdata-science\u002Ftutorial [(RSS)](https:\u002F\u002Fwww.codementor.io\u002Fdata-science\u002Ftutorial\u002Ffeed)\n* Data Science Vademecum http:\u002F\u002Fdatasciencevademecum.wordpress.com\u002F [(RSS)](http:\u002F\u002Fdatasciencevademecum.wordpress.com\u002Ffeed\u002F)\n* Dataaspirant http:\u002F\u002Fdataaspirant.com\u002F [(RSS)](http:\u002F\u002Fdataaspirant.wordpress.com\u002Ffeed\u002F)\n* Dataclysm http:\u002F\u002Fblog.okcupid.com\u002F [(RSS)](http:\u002F\u002Fblog.okcupid.com\u002Findex.php\u002Ffeed\u002F)\n* DataGenetics http:\u002F\u002Fdatagenetics.com\u002Fblog.html [(RSS)](http:\u002F\u002Fdatagenetics.com\u002Ffeed\u002Frss.xml)\n* Dataiku https:\u002F\u002Fwww.dataiku.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.dataiku.com\u002Ffeed.xml)\n* DataKind http:\u002F\u002Fwww.datakind.org\u002Fblog [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FDataKin)\n* DataLook http:\u002F\u002Fblog.datalook.io\u002F [(RSS)](http:\u002F\u002Fblog.datalook.io\u002Ffeed\u002F)\n* Datanice https:\u002F\u002Fdatanice.wordpress.com\u002F [(RSS)](https:\u002F\u002Fdatanice.wordpress.com\u002Ffeed\u002F)\n* Dataquest Blog https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002F [(RSS)](https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002Fatom.xml)\n* DataRobot http:\u002F\u002Fwww.datarobot.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.datarobot.com\u002Ffeed\u002F)\n* Datascope http:\u002F\u002Fdatascopeanalytics.com\u002Fblog [(RSS)](http:\u002F\u002Fdatascopeanalytics.com\u002Frss)\n* DatasFrame http:\u002F\u002Ftomaugspurger.github.io\u002F [(RSS)](http:\u002F\u002Ftomaugspurger.github.io\u002Ffeeds\u002Fall.rss.xml)\n* David Mimno http:\u002F\u002Fwww.mimno.org\u002F [(RSS)](http:\u002F\u002Fmimno.infosci.cornell.edu\u002Fb\u002Ffeed.xml)\n* Dayne Batten http:\u002F\u002Fdaynebatten.com [(RSS)](http:\u002F\u002Fdaynebatten.com\u002Ffeed\u002F)\n* Deep Learning http:\u002F\u002Fdeeplearning.net\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdeeplearning.net\u002Ffeed\u002F)\n* Deepdish http:\u002F\u002Fdeepdish.io\u002F [(RSS)](http:\u002F\u002Fdeepdish.io\u002Fatom.xml)\n* Delip Rao http:\u002F\u002Fdeliprao.com\u002F [(RSS)](http:\u002F\u002Fdeliprao.com\u002Ffeed)\n* DENNY'S BLOG http:\u002F\u002Fblog.dennybritz.com\u002F [(RSS)](http:\u002F\u002Fblog.dennybritz.com\u002Ffeed\u002F)\n* Dimensionless https:\u002F\u002Fdimensionless.in\u002Fblog\u002F [(RSS)](https:\u002F\u002Fdimensionless.in\u002Ffeed)\n* Distill http:\u002F\u002Fdistill.pub\u002F [(RSS)](http:\u002F\u002Fdistill.pub\u002Frss.xml)\n* District Data Labs http:\u002F\u002Fdistrictdatalabs.silvrback.com\u002F [(RSS)](https:\u002F\u002Fdistrictdatalabs.silvrback.com\u002Ffeed)\n* Diving into data https:\u002F\u002Fblog.datadive.net\u002F [(RSS)](http:\u002F\u002Fblog.datadive.net\u002Ffeed\u002F)\n* Domino Data Lab's blog http:\u002F\u002Fblog.dominodatalab.com\u002F [(RSS)](http:\u002F\u002Fblog.dominodatalab.com\u002Frss\u002F)\n* Dr. Randal S. Olson http:\u002F\u002Fwww.randalolson.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.randalolson.com\u002Ffeed\u002F)\n* Drew Conway https:\u002F\u002Fmedium.com\u002F@drewconway [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@drewconway)\n* Dustin Tran http:\u002F\u002Fdustintran.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdustintran.com\u002Fblog\u002Frss\u002F)\n* Eder Santana https:\u002F\u002Federsantana.github.io\u002Fblog.html [(RSS)](http:\u002F\u002Federsantana.github.io\u002Ffeed.xml)\n* Edwin Chen http:\u002F\u002Fblog.echen.me [(RSS)](http:\u002F\u002Fblog.echen.me\u002Ffeeds\u002Fall.rss.xml)\n* EFavDB http:\u002F\u002Fefavdb.com\u002F [(RSS)](http:\u002F\u002Fefavdb.com\u002Ffeed\u002F)\n* Emilio Ferrara, Ph.D.  http:\u002F\u002Fwww.emilio.ferrara.name\u002F [(RSS)](http:\u002F\u002Fwww.emilio.ferrara.name\u002Ffeed\u002F)\n* Entrepreneurial Geekiness http:\u002F\u002Fianozsvald.com\u002F [(RSS)](http:\u002F\u002Fianozsvald.com\u002Ffeed\u002F)\n* Eric Jonas http:\u002F\u002Fericjonas.com\u002Farchives.html [(RSS)](http:\u002F\u002Fericjonas.com\u002Farchives.html)\n* Eric Siegel http:\u002F\u002Fwww.predictiveanalyticsworld.com\u002Fblog [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fpredictiveanalyticsworld\u002FGXRy)\n* Erik Bern http:\u002F\u002Ferikbern.com [(RSS)](http:\u002F\u002Ferikbern.com\u002Ffeed\u002F)\n* ERIN SHELLMAN http:\u002F\u002Fwww.erinshellman.com\u002F [(RSS)](http:\u002F\u002Fwww.erinshellman.com\u002Ffeed\u002F)\n* Eugenio Culurciello http:\u002F\u002Fculurciello.github.io\u002F [(RSS)](http:\u002F\u002Fculurciello.github.io\u002Ffeed.xml)\n* Fabian Pedregosa http:\u002F\u002Ffa.bianp.net\u002F [(RSS)](http:\u002F\u002Ffa.bianp.net\u002Fblog\u002Ffeed\u002F)\n* Fast Forward Labs http:\u002F\u002Fblog.fastforwardlabs.com\u002F [(RSS)](http:\u002F\u002Fblog.fastforwardlabs.com\u002Frss)\n* FastML http:\u002F\u002Ffastml.com\u002F [(RSS)](http:\u002F\u002Ffastml.com\u002Fatom.xml)\n* Florian Hartl http:\u002F\u002Fflorianhartl.com\u002F [(RSS)](http:\u002F\u002Fflorianhartl.com\u002Ffeed\u002F)\n* FlowingData http:\u002F\u002Fflowingdata.com\u002F [(RSS)](http:\u002F\u002Fflowingdata.com\u002Ffeed\u002F)\n* Full Stack ML http:\u002F\u002Ffullstackml.com\u002F [(RSS)](http:\u002F\u002Ffullstackml.com\u002Ffeed\u002F)\n* GAB41 http:\u002F\u002Fwww.lab41.org\u002Fgab41\u002F [(RSS)](http:\u002F\u002Fwww.lab41.org\u002Ffeed\u002F)\n* Garbled Notes http:\u002F\u002Fwww.chioka.in\u002F [(RSS)](http:\u002F\u002Fwww.chioka.in\u002Ffeed.xml)\n* Greg Reda http:\u002F\u002Fwww.gregreda.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.gregreda.com\u002Ffeeds\u002Fall.atom.xml)\n* Hyon S Chu https:\u002F\u002Fmedium.com\u002F@adailyventure [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@adailyventure)\n* i am trask http:\u002F\u002Fiamtrask.github.io\u002F [(RSS)](http:\u002F\u002Fiamtrask.github.io\u002Ffeed.xml)\n* I Quant NY http:\u002F\u002Fiquantny.tumblr.com\u002F [(RSS)](http:\u002F\u002Fiquantny.tumblr.com\u002Frss)\n* inFERENCe http:\u002F\u002Fwww.inference.vc\u002F [(RSS)](http:\u002F\u002Fwww.inference.vc\u002Frss\u002F)\n* Insight Data Science https:\u002F\u002Fblog.insightdatascience.com\u002F [(RSS)](https:\u002F\u002Fblog.insightdatascience.com\u002Ffeed)\n* INSPIRATION INFORMATION http:\u002F\u002Fmyinspirationinformation.com\u002F [(RSS)](http:\u002F\u002Fmyinspirationinformation.com\u002Ffeed\u002F)\n* Ira Korshunova http:\u002F\u002Firakorshunova.github.io\u002F [(RSS)](http:\u002F\u002Firakorshunova.github.io\u002Ffeed.xml)\n* I’m a bandit https:\u002F\u002Fblogs.princeton.edu\u002Fimabandit\u002F [(RSS)](https:\u002F\u002Fblogs.princeton.edu\u002Fimabandit\u002Ffeed\u002F)\n* Jason Toy http:\u002F\u002Fwww.jtoy.net\u002F [(RSS)](http:\u002F\u002Fjtoy.net\u002Fatom.xml)\n* Jeremy D. Jackson, PhD http:\u002F\u002Fwww.jeremydjacksonphd.com\u002F [(RSS)](http:\u002F\u002Fwww.jeremydjacksonphd.com\u002F?feed=rss2)\n* Jesse Steinweg-Woods https:\u002F\u002Fjessesw.com\u002F [(RSS)](https:\u002F\u002Fjessesw.com\u002Ffeed.xml)\n* Joe Cauteruccio http:\u002F\u002Fwww.joecjr.com\u002F [(RSS)](http:\u002F\u002Fwww.joecjr.com\u002Ffeed\u002F)\n* John Myles White http:\u002F\u002Fwww.johnmyleswhite.com\u002F [(RSS)](http:\u002F\u002Fwww.johnmyleswhite.com\u002Ffeed\u002F)\n* John's Soapbox http:\u002F\u002Fjoschu.github.io\u002F [(RSS)](http:\u002F\u002Fjoschu.github.io\u002Ffeed.xml)\n* Jonas Degrave http:\u002F\u002F317070.github.io\u002F [(RSS)](http:\u002F\u002F317070.github.io\u002Ffeed.xml)\n* Joy Of Data http:\u002F\u002Fwww.joyofdata.de\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.joyofdata.de\u002Fblog\u002Ffeed\u002F)\n* Julia Evans http:\u002F\u002Fjvns.ca\u002F [(RSS)](http:\u002F\u002Fjvns.ca\u002Fatom.xml)\n* KDnuggets http:\u002F\u002Fwww.kdnuggets.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fkdnuggets-data-mining-analytics)\n* Keeping Up With The Latest Techniques http:\u002F\u002Fcolinpriest.com\u002F [(RSS)](http:\u002F\u002Fcolinpriest.com\u002Ffeed\u002F)\n* Kenny Bastani http:\u002F\u002Fwww.kennybastani.com\u002F [(RSS)](http:\u002F\u002Fwww.kennybastani.com\u002Ffeeds\u002Fposts\u002Fdefault?alt=rss)\n* Kevin Davenport http:\u002F\u002Fkldavenport.com\u002F [(RSS)](http:\u002F\u002Fkldavenport.com\u002Ffeed\u002F)\n* kevin frans http:\u002F\u002Fkvfrans.com\u002F [(RSS)](http:\u002F\u002Fkvfrans.com\u002Frss\u002F)\n* korbonits | Math ∩ Data http:\u002F\u002Fkorbonits.github.io\u002F [(RSS)](http:\u002F\u002Fkorbonits.github.io\u002Ffeed.xml)\n* Large Scale Machine Learning  http:\u002F\u002Fbickson.blogspot.com\u002F [(RSS)](http:\u002F\u002Fbickson.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* LATERAL BLOG https:\u002F\u002Fblog.lateral.io\u002F [(RSS)](https:\u002F\u002Fblog.lateral.io\u002Ffeed\u002F)\n* Lazy Programmer http:\u002F\u002Flazyprogrammer.me\u002F [(RSS)](http:\u002F\u002Flazyprogrammer.me\u002Ffeed\u002F)\n* Learn Analytics Here https:\u002F\u002Flearnanalyticshere.wordpress.com\u002F [(RSS)](https:\u002F\u002Flearnanalyticshere.wordpress.com\u002Ffeed\u002F)\n* LearnDataSci http:\u002F\u002Fwww.learndatasci.com\u002F [(RSS)](http:\u002F\u002Fwww.learndatasci.com\u002Ffeed\u002F)\n* Learning With Data http:\u002F\u002Flearningwithdata.com\u002F [(RSS)](http:\u002F\u002Flearningwithdata.com\u002Frss_feed.xml)\n* Life, Language, Learning http:\u002F\u002Fdaoudclarke.github.io\u002F [(RSS)](http:\u002F\u002Fdaoudclarke.github.io\u002Fatom.xml)\n* Locke Data https:\u002F\u002Fitsalocke.com\u002Fblog\u002F [(RSS)](https:\u002F\u002Fitsalocke.com\u002Ffeed)\n* Louis Dorard http:\u002F\u002Fwww.louisdorard.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.louisdorard.com\u002Fblog?format=rss)\n* M.E.Driscoll http:\u002F\u002Fmedriscoll.com\u002F [(RSS)](http:\u002F\u002Fmedriscoll.com\u002Frss)\n* Machinalis http:\u002F\u002Fwww.machinalis.com\u002Fblog [(RSS)](http:\u002F\u002Fwww.machinalis.com\u002Fblog\u002Ffeeds\u002Frss\u002F)\n* Machine Learning (Theory) http:\u002F\u002Fhunch.net\u002F [(RSS)](http:\u002F\u002Fhunch.net\u002F?feed=rss2)\n* Machine Learning and Data Science http:\u002F\u002Falexhwoods.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Falexhwoods.com\u002Ffeed\u002F)\n* Machine Learning https:\u002F\u002Fcharlesmartin14.wordpress.com\u002F [(RSS)](http:\u002F\u002Fcharlesmartin14.wordpress.com\u002Ffeed\u002F)\n* Machine Learning Mastery http:\u002F\u002Fmachinelearningmastery.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmachinelearningmastery.com\u002Ffeed\u002F)\n* Machine Learning Blogs https:\u002F\u002Fmachinelearningblogs.com\u002F [(RSS)](https:\u002F\u002Fmachinelearningblogs.com\u002Ffeed\u002F)\n* Machine Learning, etc http:\u002F\u002Fyaroslavvb.blogspot.com [(RSS)](http:\u002F\u002Fyaroslavvb.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Machine Learning, Maths and Physics https:\u002F\u002Fmlopezm.wordpress.com\u002F [(RSS)](https:\u002F\u002Fmlopezm.wordpress.com\u002Ffeed\u002F)\n* Machine Learning Flashcards https:\u002F\u002Fmachinelearningflashcards.com\u002F $10, but a nicely illustrated set of 300 flash cards\n* Machined Learnings http:\u002F\u002Fwww.machinedlearnings.com\u002F [(RSS)](http:\u002F\u002Fwww.machinedlearnings.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* MAPPING BABEL https:\u002F\u002Fjack-clark.net\u002F [(RSS)](https:\u002F\u002Fjack-clark.net\u002Ffeed\u002F)\n* MAPR Blog https:\u002F\u002Fwww.mapr.com\u002Fblog [(RSS)](https:\u002F\u002Fwww.mapr.com\u002Fbigdata.xml)\n* MAREK REI http:\u002F\u002Fwww.marekrei.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.marekrei.com\u002Fblog\u002Ffeed\u002F)\n* MARGINALLY INTERESTING http:\u002F\u002Fblog.mikiobraun.de\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FMarginallyInteresting)\n* Math ∩ Programming http:\u002F\u002Fjeremykun.com\u002F [(RSS)](http:\u002F\u002Fjeremykun.wordpress.com\u002Ffeed\u002F)\n* Matthew Rocklin http:\u002F\u002Fmatthewrocklin.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmatthewrocklin.com\u002Fblog\u002Fatom.xml)\n* Melody Wolk http:\u002F\u002Fmelodywolk.com\u002Fprojects\u002F [(RSS)](http:\u002F\u002Fmelodywolk.com\u002Ffeed\u002F)\n* Mic Farris http:\u002F\u002Fwww.micfarris.com\u002F [(RSS)](http:\u002F\u002Fwww.micfarris.com\u002Ffeed\u002F)\n* Mike Tyka http:\u002F\u002Fmtyka.github.io\u002F [(RSS)](http:\u002F\u002Fmtyka.github.io\u002F\u002Ffeed.xml)\n* minimaxir | Max Woolf's Blog http:\u002F\u002Fminimaxir.com\u002F [(RSS)](http:\u002F\u002Fminimaxir.com\u002Frss.xml)\n* Mirror Image https:\u002F\u002Fmirror2image.wordpress.com\u002F [(RSS)](http:\u002F\u002Fmirror2image.wordpress.com\u002Ffeed\u002F)\n* Mitch Crowe http:\u002F\u002Fwww.dataphoric.com\u002F [(RSS)](http:\u002F\u002Fwww.dataphoric.com\u002Ffeed.xml)\n* MLWave http:\u002F\u002Fmlwave.com\u002F [(RSS)](http:\u002F\u002Fmlwave.com\u002Ffeed\u002F)\n* MLWhiz http:\u002F\u002Fmlwhiz.com\u002F [(RSS)](http:\u002F\u002Fmlwhiz.com\u002Fatom.xml)\n* Models are illuminating and wrong https:\u002F\u002Fpeadarcoyle.wordpress.com\u002F [(RSS)](http:\u002F\u002Fpeadarcoyle.wordpress.com\u002Ffeed\u002F)\n* Moody Rd http:\u002F\u002Fblog.mrtz.org\u002F [(RSS)](http:\u002F\u002Fblog.mrtz.org\u002Ffeed.xml)\n* Moonshots http:\u002F\u002Fjxieeducation.com\u002F [(RSS)](http:\u002F\u002Fjxieeducation.com\u002Ffeed.xml)\n* Mourad Mourafiq http:\u002F\u002Fmourafiq.com\u002F [(RSS)](http:\u002F\u002Fmourafiq.com\u002Fatom.xml)\n* My thoughts on Data science, predictive analytics, Python http:\u002F\u002Fshahramabyari.com\u002F [(RSS)](http:\u002F\u002Fshahramabyari.com\u002Ffeed\u002F)\n* Natural language processing blog http:\u002F\u002Fnlpers.blogspot.fr\u002F [(RSS)](http:\u002F\u002Fnlpers.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Neil Lawrence http:\u002F\u002Finverseprobability.com\u002Fblog.html [(RSS)](http:\u002F\u002Finverseprobability.com\u002Frss.xml)\n* NLP and Deep Learning enthusiast http:\u002F\u002Fcamron.xyz\u002F [(RSS)](http:\u002F\u002Fcamron.xyz\u002Findex.php\u002Ffeed\u002F)\n* no free hunch http:\u002F\u002Fblog.kaggle.com\u002F [(RSS)](http:\u002F\u002Fblog.kaggle.com\u002Ffeed\u002F)\n* Nuit Blanche http:\u002F\u002Fnuit-blanche.blogspot.com\u002F [(RSS)](http:\u002F\u002Fnuit-blanche.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Number 2147483647 https:\u002F\u002Fno2147483647.wordpress.com\u002F [(RSS)](http:\u002F\u002Fno2147483647.wordpress.com\u002Ffeed\u002F)\n* On Machine Intelligence https:\u002F\u002Faimatters.wordpress.com\u002F [(RSS)](https:\u002F\u002Faimatters.wordpress.com\u002Ffeed\u002F)\n* Opiate for the masses Data is our religion. http:\u002F\u002Fopiateforthemass.es\u002F [(RSS)](http:\u002F\u002Fopiateforthemass.es\u002Ffeed.xml)\n* p-value.info http:\u002F\u002Fwww.p-value.info\u002F [(RSS)](http:\u002F\u002Fwww.p-value.info\u002Ffeeds\u002Fposts\u002Fdefault)\n* Pete Warden's blog http:\u002F\u002Fpetewarden.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Ftypepad\u002Fpetewarden)\n* Plotly Blog http:\u002F\u002Fblog.plot.ly\u002F [(RSS)](http:\u002F\u002Fblog.plot.ly\u002Frss)\n* Probably Overthinking It http:\u002F\u002Fallendowney.blogspot.ca\u002F [(RSS)](http:\u002F\u002Fallendowney.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Prooffreader.com http:\u002F\u002Fwww.prooffreader.com [(RSS)](http:\u002F\u002Fwww.prooffreader.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* ProoffreaderPlus http:\u002F\u002Fprooffreaderplus.blogspot.ca\u002F [(RSS)](http:\u002F\u002Fprooffreaderplus.blogspot.ca\u002Ffeeds\u002Fposts\u002Fdefault)\n* Publishable Stuff http:\u002F\u002Fwww.sumsar.net\u002F [(RSS)](http:\u002F\u002Fwww.sumsar.net\u002Fatom.xml)\n* PyImageSearch http:\u002F\u002Fwww.pyimagesearch.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FPyimagesearch)\n* Pythonic Perambulations https:\u002F\u002Fjakevdp.github.io\u002F [(RSS)](http:\u002F\u002Fjakevdp.github.com\u002Fatom.xml)\n* quintuitive http:\u002F\u002Fquintuitive.com\u002F [(RSS)](http:\u002F\u002Fquintuitive.com\u002Ffeed\u002F)\n* R and Data Mining https:\u002F\u002Frdatamining.wordpress.com\u002F [(RSS)](http:\u002F\u002Frdatamining.wordpress.com\u002Ffeed\u002F)\n* R-bloggers http:\u002F\u002Fwww.r-bloggers.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FRBloggers)\n* R2RT http:\u002F\u002Fr2rt.com\u002F [(RSS)](http:\u002F\u002Fr2rt.com\u002Ffeeds\u002Fall.atom.xml)\n* Ramiro Gómez http:\u002F\u002Framiro.org\u002Fnotebooks\u002F [(RSS)](http:\u002F\u002Framiro.org\u002Fnotebook\u002Frss.xml)\n* Random notes on Computer Science, Mathematics and Software Engineering http:\u002F\u002Fbarmaley-exe.github.io\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fbarmaley-exe-blog-feed)\n* Randy Zwitch http:\u002F\u002Frandyzwitch.com\u002F [(RSS)](http:\u002F\u002Frandyzwitch.com\u002Ffeed.xml)\n* RaRe Technologies http:\u002F\u002Frare-technologies.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Frare-technologies.com\u002Ffeed\u002F)\n* Rayli.Net http:\u002F\u002Frayli.net\u002Fblog\u002F [(RSS)](http:\u002F\u002Frayli.net\u002Fblog\u002Ffeed\u002F)\n* Revolutions http:\u002F\u002Fblog.revolutionanalytics.com\u002F [(RSS)](http:\u002F\u002Fblog.revolutionanalytics.com\u002Fatom.xml)\n* Rinu Boney http:\u002F\u002Frinuboney.github.io\u002F [(RSS)](http:\u002F\u002Frinuboney.github.io\u002Ffeed.xml)\n* RNDuja Blog http:\u002F\u002Frnduja.github.io\u002F [(RSS)](http:\u002F\u002Frnduja.github.io\u002Ffeed.xml)\n* Robert Chang https:\u002F\u002Fmedium.com\u002F@rchang [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@rchang)\n* Rocket-Powered Data Science http:\u002F\u002Frocketdatascience.org [(RSS)](http:\u002F\u002Frocketdatascience.org\u002F?feed=rss2)\n* Sachin Joglekar's blog https:\u002F\u002Fcodesachin.wordpress.com\u002F [(RSS)](https:\u002F\u002Fcodesachin.wordpress.com\u002Ffeed\u002F)\n* samim https:\u002F\u002Fmedium.com\u002F@samim [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@samim)\n* Sean J. Taylor http:\u002F\u002Fseanjtaylor.com\u002F [(RSS)](http:\u002F\u002Fseanjtaylor.com\u002Frss)\n* Sebastian Raschka http:\u002F\u002Fsebastianraschka.com\u002Fblog\u002Findex.html [(RSS)](http:\u002F\u002Fsebastianraschka.com\u002Frss_feed.xml)\n* Sebastian Ruder http:\u002F\u002Fsebastianruder.com\u002F [(RSS)](http:\u002F\u002Fsebastianruder.com\u002Frss\u002F)\n* Sebastian's slow blog http:\u002F\u002Fwww.nowozin.net\u002Fsebastian\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.nowozin.net\u002Fsebastian\u002Fblog\u002Ffeeds\u002Fall.atom.xml)\n* SFL Scientific Blog https:\u002F\u002Fsflscientific.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fsflscientific.com\u002Fblog\u002F?format=rss)\n* Shakir's Machine Learning Blog http:\u002F\u002Fblog.shakirm.com\u002F [(RSS)](http:\u002F\u002Fblog.shakirm.com\u002Ffeed\u002F)\n* Simply Statistics http:\u002F\u002Fsimplystatistics.org [(RSS)](http:\u002F\u002Fsimplystatistics.org\u002Ffeed\u002F)\n* Springboard Blog http:\u002F\u002Fspringboard.com\u002Fblog\n* Startup.ML Blog http:\u002F\u002Fstartup.ml\u002Fblog [(RSS)](http:\u002F\u002Fwww.startup.ml\u002Fblog?format=RSS)\n* Statistical Modeling, Causal Inference, and Social Science http:\u002F\u002Fandrewgelman.com\u002F [(RSS)](http:\u002F\u002Fandrewgelman.com\u002Ffeed\u002F)\n* Stigler Diet http:\u002F\u002Fstiglerdiet.com\u002F [(RSS)](http:\u002F\u002Fstiglerdiet.com\u002Ffeeds\u002Fall.atom.xml)\n* Stitch Fix Tech Blog http:\u002F\u002Fmultithreaded.stitchfix.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmultithreaded.stitchfix.com\u002Ffeed.xml)\n* Stochastic R&D Notes http:\u002F\u002Farseny.info\u002F [(RSS)](http:\u002F\u002Farseny.info\u002Ffeeds\u002Fall.rss.xml)\n* Storytelling with Statistics on Quora http:\u002F\u002Fdatastories.quora.com\u002F [(RSS)](http:\u002F\u002Fdatastories.quora.com\u002Frss)\n* StreamHacker http:\u002F\u002Fstreamhacker.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FStreamHacker)\n* Subconscious Musings http:\u002F\u002Fblogs.sas.com\u002Fcontent\u002Fsubconsciousmusings\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fadvanalytics)\n* Swan Intelligence http:\u002F\u002Fswanintelligence.com\u002F [(RSS)](http:\u002F\u002Fswanintelligence.com\u002Ffeeds\u002Fall.rss.xml)\n* TechnoCalifornia http:\u002F\u002Ftechnocalifornia.blogspot.se\u002F [(RSS)](http:\u002F\u002Ftechnocalifornia.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* TEXT ANALYSIS BLOG | AYLIEN http:\u002F\u002Fblog.aylien.com\u002F [(RSS)](http:\u002F\u002Fblog.aylien.com\u002Frss)\n* The Angry Statistician http:\u002F\u002Fangrystatistician.blogspot.com\u002F [(RSS)](http:\u002F\u002Fangrystatistician.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* The Clever Machine https:\u002F\u002Ftheclevermachine.wordpress.com\u002F [(RSS)](http:\u002F\u002Ftheclevermachine.wordpress.com\u002Ffeed\u002F)\n* The Data Camp Blog https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Fblog [(RSS)](http:\u002F\u002Fblog.datacamp.com\u002Ffeed\u002F)\n* The Data Incubator http:\u002F\u002Fblog.thedataincubator.com\u002F [(RSS)](http:\u002F\u002Fblog.thedataincubator.com\u002Ffeed\u002F)\n* The Data Science Lab https:\u002F\u002Fdatasciencelab.wordpress.com\u002F [(RSS)](http:\u002F\u002Fdatasciencelab.wordpress.com\u002Ffeed\u002F)\n* THE ETZ-FILES http:\u002F\u002Falexanderetz.com\u002F [(RSS)](http:\u002F\u002Fnicebrain.wordpress.com\u002Ffeed\u002F)\n* The Science of Data http:\u002F\u002Fwww.martingoodson.com [(RSS)](http:\u002F\u002Fwww.martingoodson.com\u002Frss\u002F)\n* The Shape of Data https:\u002F\u002Fshapeofdata.wordpress.com [(RSS)](https:\u002F\u002Fshapeofdata.wordpress.com\u002Ffeed\u002F)\n* The unofficial Google data science Blog http:\u002F\u002Fwww.unofficialgoogledatascience.com\u002F [(RSS)](http:\u002F\u002Fwww.unofficialgoogledatascience.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Tim Dettmers http:\u002F\u002Ftimdettmers.com\u002F [(RSS)](http:\u002F\u002Ftimdettmers.com\u002Ffeed\u002F)\n* Tombone's Computer Vision Blog http:\u002F\u002Fwww.computervisionblog.com\u002F [(RSS)](http:\u002F\u002Fwww.computervisionblog.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Tommy Blanchard http:\u002F\u002Ftommyblanchard.com\u002Fcategory\u002Fprojects [(RSS)](http:\u002F\u002Ftommyblanchard.com\u002Ffeeds\u002Fall.atom.xml)\n* Trevor Stephens http:\u002F\u002Ftrevorstephens.com\u002F [(RSS)](http:\u002F\u002Ftrevorstephens.com\u002Ffeed.xml)\n* Trey Causey http:\u002F\u002Ftreycausey.com\u002F [(RSS)](http:\u002F\u002Ftreycausey.com\u002Ffeeds\u002Fall.atom.xml)\n* UW Data Science Blog http:\u002F\u002Fdatasciencedegree.wisconsin.edu\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdatasciencedegree.wisconsin.edu\u002Ffeed\u002F)\n* Wellecks http:\u002F\u002Fwellecks.wordpress.com\u002F [(RSS)](http:\u002F\u002Fwellecks.wordpress.com\u002Ffeed\u002F)\n* Wes McKinney http:\u002F\u002Fwesmckinney.com\u002Farchives.html [(RSS)](http:\u002F\u002Fwesmckinney.com\u002Ffeeds\u002Fall.atom.xml)\n* While My MCMC Gently Samples http:\u002F\u002Ftwiecki.github.io\u002F [(RSS)](http:\u002F\u002Ftwiecki.github.io\u002Fatom.xml)\n* WildML http:\u002F\u002Fwww.wildml.com\u002F [(RSS)](http:\u002F\u002Fwww.wildml.com\u002Ffeed\u002F)\n* Will do stuff for stuff http:\u002F\u002Frinzewind.org\u002Fblog-en [(RSS)](http:\u002F\u002Frinzewind.org\u002Ffeed-en)\n* Will wolf http:\u002F\u002Fwillwolf.io\u002F [(RSS)](http:\u002F\u002Fwillwolf.io\u002Ffeed\u002F)\n* WILL'S NOISE http:\u002F\u002Fwww.willmcginnis.com\u002F [(RSS)](http:\u002F\u002Fwww.willmcginnis.com\u002Ffeed\u002F)\n* William Lyon http:\u002F\u002Fwww.lyonwj.com\u002F [(RSS)](http:\u002F\u002Fwww.lyonwj.com\u002Fatom.xml)\n* Win-Vector Blog http:\u002F\u002Fwww.win-vector.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.win-vector.com\u002Fblog\u002Ffeed\u002F)\n* Yanir Seroussi http:\u002F\u002Fyanirseroussi.com\u002F [(RSS)](http:\u002F\u002Fyanirseroussi.com\u002Ffeed\u002F)\n* Zac Stewart http:\u002F\u002Fzacstewart.com\u002F [(RSS)](http:\u002F\u002Fzacstewart.com\u002Ffeed.xml)\n* ŷhat http:\u002F\u002Fblog.yhat.com\u002F [(RSS)](http:\u002F\u002Fblog.yhat.com\u002Frss.xml)\n* ℚuantitative √ourney http:\u002F\u002Foutlace.com\u002F [(RSS)](http:\u002F\u002Foutlace.com\u002Ffeed.xml)\n* 大トロ http:\u002F\u002Fblog.otoro.net\u002F [(RSS)](http:\u002F\u002Fblog.otoro.net\u002Ffeed.xml)\n\n\n## credits\n\n* [Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython](http:\u002F\u002Fwww.amazon.com\u002FPython-Data-Analysis-Wrangling-IPython\u002Fdp\u002F1449319793) by Wes McKinney\n* [PyCon 2015 Scikit-learn Tutorial](https:\u002F\u002Fgithub.com\u002Fjakevdp\u002Fsklearn_pycon2015) by Jake VanderPlas\n* [Python Data Science Handbook](https:\u002F\u002Fgithub.com\u002Fjakevdp\u002FPythonDataScienceHandbook) by Jake VanderPlas\n* [Parallel Machine Learning with scikit-learn and IPython](https:\u002F\u002Fgithub.com\u002Fogrisel\u002Fparallel_ml_tutorial) by Olivier Grisel\n* [Statistical Interference Using Computational Methods in Python](https:\u002F\u002Fgithub.com\u002FAllenDowney\u002FCompStats) by Allen Downey\n* [TensorFlow Examples](https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples) by Aymeric Damien\n* [TensorFlow Tutorials](https:\u002F\u002Fgithub.com\u002Fpkmital\u002Ftensorflow_tutorials) by Parag K Mital\n* [TensorFlow Tutorials](https:\u002F\u002Fgithub.com\u002Fnlintz\u002FTensorFlow-Tutorials) by Nathan Lintz\n* [TensorFlow Tutorials](https:\u002F\u002Fgithub.com\u002Falrojo\u002Ftensorflow-tutorial) by Alexander R Johansen\n* [TensorFlow Book](https:\u002F\u002Fgithub.com\u002FBinRoot\u002FTensorFlow-Book) by Nishant Shukla\n* [Summer School 2015](https:\u002F\u002Fgithub.com\u002Fmila-udem\u002Fsummerschool2015) by mila-udem\n* [Keras tutorials](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow) by Valerio Maggio\n* [Kaggle](https:\u002F\u002Fwww.kaggle.com\u002F)\n* [Yhat Blog](http:\u002F\u002Fblog.yhat.com\u002F)\n\n## contributing\n\nContributions are welcome!  For bug reports or requests please [submit an issue](https:\u002F\u002Fgithub.com\u002Ftarrysingh\u002FMachine-Learning-Tutorials\u002F\u002Fissues).\n\n## contact-info\n\nFeel free to contact me to discuss any issues, questions, or comments.\n\n* Email: [tarry.singh@gmail.com](mailto:tarry.singh@gmail.com)\n* Twitter: [@tarrysingh](https:\u002F\u002Ftwitter.com\u002Ftarrysingh)\n* GitHub: [tarrysingh](https:\u002F\u002Fgithub.com\u002Ftarrysingh.com)\n* LinkedIn: [Tarry Singh](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Ftarrysingh)\n* Website: [tarrysingh.com](https:\u002F\u002Ftarrysingh.com)\n* Medium: [tarry@Medium](https:\u002F\u002Fmedium.com\u002F@tarrysingh)\n* Quora : [Answers from Tarry on Quora](https:\u002F\u002Fwww.quora.com\u002Fprofile\u002FTarry-Singh)\n\n## license\n\nThis repository contains a variety of content; some developed by Tarry Singh and some from third-parties and a lot will be maintained by me. The third-party content is distributed under the license provided by those parties.\n\nThe content was originally started by Donne Martin is distributed under the following license in 2017. I have been further developing and maintaining it by adding PyTorch, Torch\u002FLua, MXNET and much more:\n\n*I am providing code and resources in this repository to you under an open source license.*\n\n    Copyright 2017 Tarry Singh\n\n    Licensed under the Apache License, Version 2.0 (the \"License\");\n    you may not use this file except in compliance with the License.\n    You may obtain a copy of the License at\n\n       http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\n    Unless required by applicable law or agreed to in writing, software\n    distributed under the License is distributed on an \"AS IS\" BASIS,\n    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n    See the License for the specific language governing permissions and\n    limitations under the License.\n","# 2023-2024 新列表：机器学习\u002F深度学习\u002FAI + Web3 教程\n\n嗨，感谢您的光临！\u003Cbr>\n\u003Cbr>\n我将每天更新这个教程网站，添加2022年至2024年所有相关主题，尤其是关于**GPU编程、以数据为中心的AI、以及诸如Web3AI.js（DeFi、DAO、NFT）等新兴话题，还有更多内容**。\u003Cbr>\n\n**注意：所有这些教程都在NVIDIA GPU上得到支持和加速**\n\u003Cbr>\n更重要的是，ML\u002FDL\u002FAI在交通、医学\u002F医疗保健等行业领域的应用，将是我密切关注并乐于与您分享的内容。\n\u003Cbr>\n最后，为了使这个网站更加实用、不那么枯燥，我非常需要您的帮助，请多多建议、评论或贡献吧！\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_07e0d6db9002.png\">\n\u003C\u002Fp>\n\n## 索引\n\n* [深度学习](#deep-learning)\n   * [优步 | Pyro](#uber-pyro-probabalistic-tutorials)\n   * [Netflix | VectorFlow](#netflix-vectorflow-tutorials)\n   * [PyTorch](#pytorch-tutorials)\n   * [TensorFlow](#tensor-flow-tutorials)\n   * [Theano](#theano-tutorials)\n   * [Keras](#keras-tutorials)\n   * [Caffe](#deep-learning-misc)\n   * [Torch\u002FLua]()\n   * [MXNET]()\n   \n* [scikit-learn](#scikit-learn)\n* [统计推断-scipy](#statistical-inference-scipy)\n* [pandas](#pandas)\n* [matplotlib](#matplotlib)\n* [numpy](#numpy)\n* [python数据](#python-data)\n* [kaggle与商业分析](#kaggle-and-business-analyses)\n* [spark](#spark)\n* [mapreduce-python](#mapreduce-python)\n* [亚马逊云服务](#aws)\n* [命令行](#commands)\n* [杂项](#misc)\n* [notebook安装](#notebook-installation)\n* [精选深度学习\u002FAI博客列表](#curated-list-of-deeplearning-blogs)\n* [致谢](#credits)\n* [贡献](#contributing)\n* [联系方式](#contact-info)\n* [许可证](#license)\n\n## 深度学习\n\n使用IPython Notebook及其他编程工具，如Torch\u002FLua\u002FD语言，来演示深度学习功能。\n\n### 优步-Pyro概率论教程\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_2655e2ef08a7.png\">\n\u003C\u002Fp>\n\n更多PyRo教程：\n\n* [PyRo示例\u002F完整示例](http:\u002F\u002Fpyro.ai\u002Fexamples\u002F)\n* [PyRo示例\u002F变分自编码器](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fvae.html)\n* [PyRo示例\u002F贝叶斯回归](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fbayesian_regression.html)\n* [PyRo示例\u002F深度马尔可夫模型](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fdmm.html)\n* [PyRo示例\u002FAIR（Attend Infer Repeat）](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fair.html)\n* [PyRo示例\u002F半监督变分自编码器](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fss-vae.html)\n* [PyRo示例\u002F高斯混合模型](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fgmm.html)\n* [PyRo示例\u002F高斯过程](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fgp.html)\n* [PyRo示例\u002F贝叶斯优化](http:\u002F\u002Fpyro.ai\u002Fexamples\u002Fbo.html)\n* [完整的PyRo代码](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Ftree\u002Fmaster\u002Fdeep-learning\u002FUBER-pyro)\n\n\n\n### Netflix-VectorFlow教程\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_efed42c2474b.png\">\n\u003C\u002Fp>\n\n* [MNIST示例，使用D语言运行](https:\u002F\u002Fgithub.com\u002FNetflix\u002Fvectorflow\u002Ftree\u002Fmaster\u002Fexamples)\n\n### PyTorch教程\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_95e5cda72c5c.png\">\n\u003C\u002Fp>\n\n| 等级 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [初学者\u002FZakizhou](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fbeginner_source) | 学习来自Facebook的PyTorch基础知识。 |\n| [中级\u002FQuanvuong](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fintermediate_source) | 学习来自Facebook的PyTorch中级内容。 |\n| [高级\u002FChsasank](https:\u002F\u002Fgithub.com\u002Fpytorch\u002Ftutorials\u002Ftree\u002Fmaster\u002Fadvanced_source) | 学习来自Facebook的PyTorch高级内容。 |\n| [通过示例学习PyTorch - NumPy、张量与自动微分](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Ftree\u002Fmaster\u002Fpytorch) | 核心来说，PyTorch提供了两大特性：一个类似于NumPy的n维张量，但它可以在GPU上运行；以及用于构建和训练神经网络的自动微分功能。 |\n| [PyTorch - 认识autograd.Variable、梯度、神经网络](https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpytorch\u002FPyTorch%20NN%20Basics%20-%20Autograd%20Gradient%20Neural%20Network%20Loss%20Backprop.ipynb) | 在这里，我们从张量的基础知识开始，用Variable模块包裹张量，玩转nn.Module，并实现前向和反向传播函数。 |\n\n### tensor-flow-tutorials\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_fef6d0bb0d1b.png\">\n\u003C\u002Fp>\n其他 TensorFlow 教程：\n\n* [pkmital\u002Ftensorflow_tutorials](https:\u002F\u002Fgithub.com\u002Fpkmital\u002Ftensorflow_tutorials)\n* [nlintz\u002FTensorFlow-Tutorials](https:\u002F\u002Fgithub.com\u002Fnlintz\u002FTensorFlow-Tutorials)\n* [alrojo\u002Ftensorflow-tutorial](https:\u002F\u002Fgithub.com\u002Falrojo\u002Ftensorflow-tutorial)\n* [BinRoot\u002FTensorFlow-Book](https:\u002F\u002Fgithub.com\u002FBinRoot\u002FTensorFlow-Book)\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tsf-basics](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F1_intro\u002Fbasic_operations.ipynb) | 学习 TensorFlow 中的基本操作，TensorFlow 是 Google 开发的用于各种感知和语言理解任务的库。 |\n| [tsf-linear](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Flinear_regression.ipynb) | 在 TensorFlow 中实现线性回归。 |\n| [tsf-logistic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Flogistic_regression.ipynb) | 在 TensorFlow 中实现逻辑回归。 |\n| [tsf-nn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F2_basic_classifiers\u002Fnearest_neighbor.ipynb) | 在 TensorFlow 中实现最近邻算法。 |\n| [tsf-alex](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Falexnet.ipynb) | 在 TensorFlow 中实现 AlexNet。 |\n| [tsf-cnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Fconvolutional_network.ipynb) | 在 TensorFlow 中实现卷积神经网络。 |\n| [tsf-mlp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Fmultilayer_perceptron.ipynb) | 在 TensorFlow 中实现多层感知机。 |\n| [tsf-rnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F3_neural_networks\u002Frecurrent_network.ipynb) | 在 TensorFlow 中实现循环神经网络。 |\n| [tsf-gpu](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F4_multi_gpu\u002Fmultigpu_basics.ipynb) | 学习 TensorFlow 中的基本多 GPU 计算。 |\n| [tsf-gviz](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F5_ui\u002Fgraph_visualization.ipynb) | 学习 TensorFlow 中的图可视化。 |\n| [tsf-lviz](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F5_ui\u002Floss_visualization.ipynb) | 学习 TensorFlow 中的损失可视化。\n\n### tensor-flow-exercises\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [tsf-not-mnist](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F1_notmnist.ipynb) | 学习简单的数据整理，通过创建包含训练、开发和测试数据集的 pickle 文件来为 TensorFlow 准备数据。 |\n| [tsf-fully-connected](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F2_fullyconnected.ipynb) | 使用逻辑回归和神经网络在 TensorFlow 中逐步训练更深、更精确的模型。 |\n| [tsf-regularization](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F3_regularization.ipynb) | 通过训练全连接网络对 notMNIST 字符进行分类，探索正则化技术。 |\n| [tsf-convolutions](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F4_convolutions.ipynb) | 在 TensorFlow 中创建卷积神经网络。 |\n| [tsf-word2vec](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F5_word2vec.ipynb) | 在 TensorFlow 中基于 Text8 数据训练 skip-gram 模型。 |\n| [tsf-lstm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftensor-flow-exercises\u002F6_lstm.ipynb) | 在 TensorFlow 中基于 Text8 数据训练 LSTM 字符模型。\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"http:\u002F\u002Fwww.deeplearning.net\u002Fsoftware\u002Ftheano\u002F_static\u002Ftheano_logo_allblue_200x46.png\">\n\u003C\u002Fp>\n\n### theano教程\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [theano-intro](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fintro_theano\u002Fintro_theano.ipynb) | Theano简介，它允许你高效地定义、优化和评估涉及多维数组的数学表达式。它可以利用GPU，并进行高效的符号微分。 |\n| [theano-scan](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fscan_tutorial\u002Fscan_tutorial.ipynb) | 学习扫描操作，这是在Theano图中执行循环的一种机制。 |\n| [theano-logistic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Fintro_theano\u002Flogistic_regression.ipynb) | 在Theano中实现逻辑回归。 |\n| [theano-rnn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Frnn_tutorial\u002Fsimple_rnn.ipynb) | 在Theano中实现循环神经网络。 |\n| [theano-mlp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Ftheano-tutorial\u002Ftheano_mlp\u002Ftheano_mlp.ipynb) | 在Theano中实现多层感知器。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"http:\u002F\u002Fi.imgur.com\u002FL45Q8c2.jpg\">\n\u003C\u002Fp>\n\n### keras教程\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| keras | Keras是一个用Python编写的开源神经网络库。它可以运行在TensorFlow或Theano之上。 |\n| [setup](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002FREADME.md) | 了解教程目标以及如何设置你的Keras环境。 |\n| [intro-deep-learning-ann](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1%20Introduction%20-%20Deep%20Learning%20and%20ANN.ipynb) | 通过Keras和人工神经网络（ANN）入门深度学习。 |\n| [感知器和Adaline](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1.1%20Perceptron%20and%20Adaline.ipynb) | 实现感知器和自适应线性神经元。 |\n| [MLP与MNIST数据](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.%20ANN\u002F1.1.2%20MLP%20and%20MNIST.ipynb) | 对手写数字进行分类，实现MLP，训练并调试ANN |\n| [theano](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.2%20Introduction%20-%20Theano.ipynb) | 通过处理权重矩阵和梯度来学习Theano。 |\n| [keras-otto](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.3%20Introduction%20-%20Keras.ipynb) | 通过Kaggle Otto挑战来学习Keras。 |\n| [ann-mnist](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F1.4%20(Extra)%20A%20Simple%20Implementation%20of%20ANN%20for%20MNIST.ipynb) | 回顾使用Keras对MNIST数据的简单ANN实现。 |\n| [卷积神经网络](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.1%20Supervised%20Learning%20-%20ConvNets.ipynb) | 使用Keras学习卷积神经网络（CNNs）。 |\n| [conv-net-1](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.2.1%20Supervised%20Learning%20-%20ConvNet%20HandsOn%20Part%20I.ipynb) | 使用Keras识别MNIST中的手写数字——第一部分。 |\n| [conv-net-2](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.2.2%20Supervised%20Learning%20-%20ConvNet%20HandsOn%20Part%20II.ipynb) | 使用Keras识别MNIST中的手写数字——第二部分。 |\n| [keras-models](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F2.3%20Supervised%20Learning%20-%20Famous%20Models%20with%20Keras.ipynb) | 使用Keras调用预训练模型，如VGG16、VGG19、ResNet50和Inception v3。 |\n| [自动编码器](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F6.%20AutoEncoders%20and%20Embeddings\u002F6.1.%20AutoEncoders%20and%20Embeddings.ipynb) | 使用Keras学习自动编码器。 |\n| [rnn-lstm](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F7.%20Recurrent%20Neural%20Networks\u002F7.1%20RNN%20and%20LSTM.ipynb) | 使用Keras学习循环神经网络（RNNs）。 |\n| [lstm-sentence-gen](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F7.%20Recurrent%20Neural%20Networks\u002F7.2%20LSTM%20for%20Sentence%20Generation.ipynb) | 使用长短期记忆（LSTM）网络学习RNN，用于句子生成。 |\n| [nlp-deep-learning](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F6.%20AutoEncoders%20and%20Embeddings\u002F6.2%20NLP%20and%20Deep%20Learning.ipynb) | 使用ANN（人工神经网络）学习自然语言处理。 |\n| [超参数调优](https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow\u002Fblob\u002Fmaster\u002F5.%20HyperParameter%20Tuning%20and%20Transfer%20Learning\u002F5.1%20HyperParameter%20Tuning.ipynb) | 使用keras-wrapper.scikit-learn进行超参数调优。\n\n### 深度学习杂项\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [deep-dream](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fdeep-learning\u002Fdeep-dream\u002Fdream.ipynb) | 基于Caffe的计算机视觉程序，利用卷积神经网络来发现并增强图像中的模式。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_1f65a7d5139b.png\">\n\u003C\u002Fp>\n\n## scikit-learn\n\n展示 scikit-learn 功能的 IPython 笔记本。\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [intro](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-intro.ipynb) | scikit-learn 入门笔记本。scikit-learn 为 Python 增加了对大型多维数组和矩阵的支持，并提供了一个包含大量高级数学函数的库，用于对这些数组进行操作。 |\n| [knn](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-intro.ipynb#K-Nearest-Neighbors-Classifier) | 在 scikit-learn 中实现 k 近邻分类器。 |\n| [linear-reg](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-linear-reg.ipynb) | 在 scikit-learn 中实现线性回归。 |\n| [svm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-svm.ipynb) | 在 scikit-learn 中实现带核和不带核的支持向量机分类器。 |\n| [random-forest](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-random-forest.ipynb) | 在 scikit-learn 中实现随机森林分类器和回归器。 |\n| [k-means](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-k-means.ipynb) | 在 scikit-learn 中实现 k 均值聚类。 |\n| [pca](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-pca.ipynb) | 在 scikit-learn 中实现主成分分析。 |\n| [gmm](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-gmm.ipynb) | 在 scikit-learn 中实现高斯混合模型。 |\n| [validation](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscikit-learn\u002Fscikit-learn-validation.ipynb) | 在 scikit-learn 中实现验证与模型选择。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_41fa0e3dc800.png\">\n\u003C\u002Fp>\n\n## statistical-inference-scipy\n\n展示使用 SciPy 功能进行统计推断的 IPython 笔记本。\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| scipy | SciPy 是基于 Python 的 NumPy 扩展构建的一组数学算法和便捷函数集合。它通过为用户提供用于数据操作和可视化的高级命令和类，显著增强了交互式 Python 会话的功能。 |\n| [effect-size](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Feffect_size.ipynb) | 通过分析男性和女性身高的差异，探讨量化效应大小的统计指标。利用行为风险因素监测系统 (BRFSS) 的数据，估算美国成年女性和男性的平均身高及标准差。 |\n| [sampling](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Fsampling.ipynb) | 通过使用 BRFSS 数据分析美国男性和女性的平均体重，探索随机抽样方法。 |\n| [hypothesis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fscipy\u002Fhypothesis.ipynb) | 通过比较第一胎婴儿与其他婴儿的差异，探讨假设检验的方法。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_7ecca73c3570.png\">\n\u003C\u002Fp>\n\n## pandas\n\n展示 pandas 功能的 IPython Notebook。\n\n| Notebook | 描述 |\n|--------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [pandas](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002Fpandas.ipynb) | 一个用 Python 编写的用于数据处理和分析的软件库。提供用于操作数值表格和时间序列的数据结构及相应操作。 |\n| [github-data-wrangling](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fviz\u002Fblob\u002Fmaster\u002Fgithubstats\u002Fdata_wrangling.ipynb) | 通过分析 [`Viz`](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fviz) 仓库中的 GitHub 数据，学习如何加载、清洗、合并以及进行特征工程。 |\n| [Introduction-to-Pandas](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.00-Introduction-to-Pandas.ipynb) | Pandas 入门。 |\n| [Introducing-Pandas-Objects](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.01-Introducing-Pandas-Objects.ipynb) | 学习 Pandas 的对象。 |\n| [Data Indexing and Selection](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.02-Data-Indexing-and-Selection.ipynb) | 学习 Pandas 中的数据索引与选择。 |\n| [Operations-in-Pandas](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.03-Operations-in-Pandas.ipynb) | 学习在 Pandas 中对数据进行操作。 |\n| [Missing-Values](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.04-Missing-Values.ipynb) | 学习如何在 Pandas 中处理缺失数据。 |\n| [Hierarchical-Indexing](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.05-Hierarchical-Indexing.ipynb) | 学习 Pandas 中的层次化索引。 |\n| [Concat-And-Append](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.06-Concat-And-Append.ipynb) | 学习如何在 Pandas 中合并数据集：使用 concat 和 append。 |\n| [Merge-and-Join](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.07-Merge-and-Join.ipynb) | 学习如何在 Pandas 中合并数据集：使用 merge 和 join。 |\n| [Aggregation-and-Grouping](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.08-Aggregation-and-Grouping.ipynb) | 学习 Pandas 中的聚合与分组操作。 |\n| [Pivot-Tables](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.09-Pivot-Tables.ipynb) | 学习 Pandas 中的透视表。 |\n| [Working-With-Strings](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.10-Working-With-Strings.ipynb) | 学习 Pandas 中的向量化字符串操作。 |\n| [Working-with-Time-Series](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.11-Working-with-Time-Series.ipynb) | 学习如何在 Pandas 中处理时间序列数据。 |\n| [Performance-Eval-and-Query](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpandas\u002F03.12-Performance-Eval-and-Query.ipynb) | 学习高性能 Pandas：eval() 和 query() 方法。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_1f733496b99a.png\">\n\u003C\u002Fp>\n\n## matplotlib\n\n演示 matplotlib 功能的 IPython Notebook。\n\n| Notebook | 描述 |\n|-----------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [matplotlib](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002Fmatplotlib.ipynb) | Python 2D 绘图库，可在多种打印格式和跨平台的交互式环境中生成出版质量的图表。 |\n| [matplotlib-applied](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002Fmatplotlib-applied.ipynb) | 将 matplotlib 可视化应用于 Kaggle 竞赛中的探索性数据分析。学习如何创建条形图、直方图、subplot2grid 布局、归一化图表、散点图、子图以及核密度估计图。 |\n| [Introduction-To-Matplotlib](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.00-Introduction-To-Matplotlib.ipynb) | Matplotlib 入门。 |\n| [Simple-Line-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.01-Simple-Line-Plots.ipynb) | 学习 Matplotlib 中的简单折线图。 |\n| [Simple-Scatter-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.02-Simple-Scatter-Plots.ipynb) | 学习 Matplotlib 中的简单散点图。 |\n| [Errorbars.ipynb](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.03-Errorbars.ipynb) | 学习在 Matplotlib 中可视化误差。 |\n| [Density-and-Contour-Plots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.04-Density-and-Contour-Plots.ipynb) | 学习 Matplotlib 中的密度图和等高线图。 |\n| [Histograms-and-Binnings](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.05-Histograms-and-Binnings.ipynb) | 学习 Matplotlib 中的直方图、分箱和密度估计。 |\n| [Customizing-Legends](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.06-Customizing-Legends.ipynb) | 学习自定义 Matplotlib 图例。 |\n| [Customizing-Colorbars](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.07-Customizing-Colorbars.ipynb) | 学习自定义 Matplotlib 的颜色条。 |\n| [Multiple-Subplots](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.08-Multiple-Subplots.ipynb) | 学习 Matplotlib 中的多个子图。 |\n| [Text-and-Annotation](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.09-Text-and-Annotation.ipynb) | 学习 Matplotlib 中的文本和注释。 |\n| [Customizing-Ticks](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.10-Customizing-Ticks.ipynb) | 学习自定义 Matplotlib 的刻度标签。 |\n| [Settings-and-Stylesheets](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.11-Settings-and-Stylesheets.ipynb) | 学习自定义 Matplotlib：配置和样式表。 |\n| [Three-Dimensional-Plotting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.12-Three-Dimensional-Plotting.ipynb) | 学习 Matplotlib 中的三维绘图。 |\n| [Geographic-Data-With-Basemap](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.13-Geographic-Data-With-Basemap.ipynb) | 学习使用 basemap 在 Matplotlib 中处理地理数据。 |\n| [Visualization-With-Seaborn](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmatplotlib\u002F04.14-Visualization-With-Seaborn.ipynb) | 学习使用 Seaborn 进行可视化。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_d8b18f24aab6.png\">\n\u003C\u002Fp>\n\n## numpy\n\n演示 NumPy 功能的 IPython 笔记本。\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [numpy](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002Fnumpy.ipynb) | 为 Python 添加对大型多维数组和矩阵的支持，并提供大量用于操作这些数组的高级数学函数库。 |\n| [Introduction-to-NumPy](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.00-Introduction-to-NumPy.ipynb) | NumPy 简介。 |\n| [Understanding-Data-Types](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.01-Understanding-Data-Types.ipynb) | 学习 Python 中的数据类型。 |\n| [The-Basics-Of-NumPy-Arrays](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.02-The-Basics-Of-NumPy-Arrays.ipynb) | 学习 NumPy 数组的基础知识。 |\n| [Computation-on-arrays-ufuncs](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.03-Computation-on-arrays-ufuncs.ipynb) | 学习 NumPy 数组上的计算：通用函数。 |\n| [Computation-on-arrays-aggregates](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.04-Computation-on-arrays-aggregates.ipynb) | 学习聚合操作：NumPy 中的最小值、最大值以及介于两者之间的各种操作。 |\n| [Computation-on-arrays-broadcasting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.05-Computation-on-arrays-broadcasting.ipynb) | 学习数组上的计算：NumPy 中的广播机制。 |\n| [Boolean-Arrays-and-Masks](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.06-Boolean-Arrays-and-Masks.ipynb) | 学习 NumPy 中的比较、掩码和布尔逻辑。 |\n| [Fancy-Indexing](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.07-Fancy-Indexing.ipynb) | 学习 NumPy 中的高级索引技术。 |\n| [Sorting](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.08-Sorting.ipynb) | 学习 NumPy 中的数组排序方法。 |\n| [Structured-Data-NumPy](http:\u002F\u002Fnbviewer.jupyter.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fnumpy\u002F02.09-Structured-Data-NumPy.ipynb) | 学习结构化数据：NumPy 的结构化数组。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_50e2d1f52270.png\">\n\u003C\u002Fp>\n\n## python-data\n\n面向数据分析的 Python 功能演示 IPython 笔记本。\n\n| 笔记本 | 描述 |\n|-----------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------|\n| [data structures](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fstructs.ipynb) | 使用元组、列表、字典、集合学习 Python 基础知识。 |\n| [data structure utilities](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fstructs_utils.ipynb) | 学习 Python 的各种操作，如切片、range、xrange、bisect、sort、sorted、reversed、enumerate、zip 以及列表推导式。 |\n| [functions](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Ffunctions.ipynb) | 学习更高级的 Python 特性：函数作为对象、lambda 函数、闭包、*args、**kwargs 柯里化、生成器、生成器表达式、itertools。 |\n| [datetime](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fdatetime.ipynb) | 学习如何使用 Python 处理日期和时间：datetime、strftime、strptime、timedelta。 |\n| [logging](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Flogs.ipynb) | 学习使用 RotatingFileHandler 和 TimedRotatingFileHandler 进行 Python 日志记录。 |\n| [pdb](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Fpdb.ipynb) | 学习使用交互式源代码调试器在 Python 中进行调试。 |\n| [unit tests](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fpython-data\u002Funit_tests.ipynb) | 学习使用 Nose 单元测试框架进行 Python 测试。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_a5a8d34c2278.png\">\n\u003C\u002Fp>\n\n## kaggle-and-business-analyses\n\n用于 [kaggle](https:\u002F\u002Fwww.kaggle.com\u002F) 竞赛和商业分析的 IPython 笔记本。\n\n| 笔记本 | 描述 |\n|-------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------|\n| [titanic](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fkaggle\u002Ftitanic.ipynb) | 预测泰坦尼克号乘客的生存情况。学习数据清洗、探索性数据分析和机器学习。 |\n| [churn-analysis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fanalyses\u002Fchurn.ipynb) | 预测客户流失。实践逻辑回归、梯度提升分类器、支持向量机、随机森林和 k 最近邻算法。内容包括混淆矩阵、ROC 曲线、特征重要性、预测概率以及校准与区分度的讨论。|\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_9be6a5e17d4e.png\">\n\u003C\u002Fp>\n\n## spark\n\n展示 Spark 和 HDFS 功能的 IPython Notebook。\n\n| Notebook | 描述 |\n|--------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|\n| [spark](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fspark\u002Fspark.ipynb) | 基于内存的集群计算框架，在某些应用场景下速度可提升至 100 倍，非常适合机器学习算法。 |\n| [hdfs](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fspark\u002Fhdfs.ipynb) | 可靠地将超大文件存储在大型集群中的多台机器上。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_51a67b8f1e2c.png\">\n\u003C\u002Fp>\n\n## mapreduce-python\n\n展示使用 mrjob 实现 Hadoop MapReduce 功能的 IPython Notebook。\n\n| Notebook | 描述 |\n|--------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------|\n| [mapreduce-python](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmapreduce\u002Fmapreduce-python.ipynb) | 以 Python 运行 MapReduce 作业，可在本地或 Hadoop 集群上执行。演示了如何通过 Python 代码实现 Hadoop Streaming，并结合单元测试及 [mrjob](https:\u002F\u002Fgithub.com\u002FYelp\u002Fmrjob) 配置文件来分析 Amazon S3 存储桶的日志数据，运行于 Elastic MapReduce 上。[Disco](https:\u002F\u002Fgithub.com\u002Fdiscoproject\u002Fdisco\u002F) 是另一个基于 Python 的替代方案。|\n\n\u003Cbr\u002F>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_75eb0ecb9a37.png\">\n\u003C\u002Fp>\n\n## aws\n\n展示亚马逊云服务（AWS）及其工具功能的 IPython Notebook。\n\n还可查看：\n\n* [SAWS](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fsaws)：一款功能强大的 AWS 命令行界面（CLI）。\n* [Awesome AWS](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fawesome-aws)：精选的库、开源项目、指南、博客及其他资源列表。\n\n| Notebook | 描述 |\n|------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [boto](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#Boto) | AWS 官方提供的 Python SDK。 |\n| [s3cmd](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3cmd) | 通过命令行与 S3 进行交互。 |\n| [s3distcp](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3distcp) | 根据指定模式和目标文件，将较小的文件合并并聚合在一起。S3DistCp 也可用于将大量数据从 S3 传输到您的 Hadoop 集群。 |\n| [s3-parallel-put](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#s3-parallel-put) | 并行上传多个文件至 S3。 |\n| [redshift](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#redshift) | 基于大规模并行处理（MPP）技术构建的快速数据仓库。 |\n| [kinesis](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#kinesis) | 实时流式传输数据，每秒可处理数千个数据流。 |\n| [lambda](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Faws\u002Faws.ipynb#lambda) | 根据事件触发运行代码，并自动管理计算资源。 |\n\n\u003Cbr\u002F>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_readme_ab202643a12e.png\">\n\u003C\u002Fp>\n\n## 命令\n\n展示 Linux、Git 等各种命令行的 IPython Notebook。\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [linux](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Flinux.ipynb) | 类 Unix 且大部分符合 POSIX 标准的计算机操作系统。包括磁盘使用情况、文件分割、grep、sed、curl、查看运行中的进程、终端语法高亮以及 Vim。|\n| [anaconda](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#anaconda) | 面向大规模数据处理、预测分析和科学计算的 Python 编程语言发行版，旨在简化包管理和部署。 |\n| [ipython notebook](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#ipython-notebook) | 基于 Web 的交互式计算环境，可将代码执行、文本、数学公式、图表和富媒体整合到一个文档中。 |\n| [git](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#git) | 分布式版本控制系统，注重速度、数据完整性以及对分布式、非线性工作流的支持。 |\n| [ruby](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#ruby) | 用于与 AWS 命令行交互，以及 Jekyll——一个可托管在 GitHub Pages 上的博客框架。 |\n| [jekyll](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#jekyll) | 一种简单、具备博客功能的静态网站生成器，适用于个人、项目或组织的网站。它能渲染 Markdown 或 Textile 和 Liquid 模板，并生成完整的静态网站，可由 Apache HTTP Server、Nginx 或其他 Web 服务器直接提供服务。 |\n| [pelican](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#pelican) | 基于 Python 的 Jekyll 替代方案。 |\n| [django](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fcommands\u002Fmisc.ipynb#django) | 高级 Python Web 框架，鼓励快速开发和简洁实用的设计。可用于分享报告\u002F分析内容及进行博客写作。更轻量级的替代方案包括 [Pyramid](https:\u002F\u002Fgithub.com\u002FPylons\u002Fpyramid)、[Flask](https:\u002F\u002Fgithub.com\u002Fpallets\u002Fflask)、[Tornado](https:\u002F\u002Fgithub.com\u002Ftornadoweb\u002Ftornado) 和 [Bottle](https:\u002F\u002Fgithub.com\u002Fbottlepy\u002Fbottle)。\n\n## 杂项\n\n展示各种功能的 IPython Notebook。\n\n| 笔记本 | 描述 |\n|--------------------------------------------------------------------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [regex](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmisc\u002Fregex.ipynb) | 正则表达式速查表，适用于数据清洗。|\n|[algorithmia](http:\u002F\u002Fnbviewer.ipython.org\u002Fgithub\u002FTarrySingh\u002FMachine-Learning-Tutorials\u002Fblob\u002Fmaster\u002Fmisc\u002FAlgorithmia.ipynb) | Algorithmia 是一个算法市场。该笔记本展示了四种不同的算法：人脸检测、内容摘要、潜在狄利克雷分配和光学字符识别。|\n\n## 笔记本安装\n\n### anaconda\n\nAnaconda 是面向大规模数据处理、预测分析和科学计算的免费 Python 发行版，旨在简化包管理和部署。\n\n请按照说明安装 [Anaconda](https:\u002F\u002Fdocs.continuum.io\u002Fanaconda\u002Finstall) 或更轻量级的 [miniconda](http:\u002F\u002Fconda.pydata.org\u002Fminiconda.html)。\n\n### 开发环境搭建\n\n如需详细的搭建指南、脚本和工具来配置您的数据分析开发环境，请参阅 [dev-setup](https:\u002F\u002Fgithub.com\u002Fdonnemartin\u002Fdev-setup) 仓库。\n\n### 运行笔记本\n\n注意：如果您打算通过实践学习（推荐方式），我强烈建议您尽可能自己编写代码，而不是仅仅运行预先写好的代码。如果您仍然想尝试运行这些笔记本，请按以下步骤操作：\n\n要查看交互式内容或修改 IPython 笔记本中的元素，您需要先克隆或下载该仓库，然后运行笔记本。有关 IPython 笔记本的更多信息，请参阅 [这里](http:\u002F\u002Fipython.org\u002Fnotebook.html)。\n\n    $ git clone https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials.git\n    $ cd Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\n    $ jupyter notebook\n    \n\n笔记本已在 Python 3.7+ 环境下测试通过。\n\n## 深度学习博客精选列表\n\n* 一位人类工程师的博客 http:\u002F\u002Fwww.erogol.com\u002F [(RSS)](http:\u002F\u002Fwww.erogol.com\u002Ffeed\u002F)\n* Aakash Japi http:\u002F\u002Faakashjapi.com\u002F [(RSS)](http:\u002F\u002Flogicx24.github.io\u002Ffeed.xml)\n* Adit Deshpande https:\u002F\u002Fadeshpande3.github.io\u002F [(RSS)](https:\u002F\u002Fadeshpande3.github.io\u002Fadeshpande3.github.io\u002Ffeed.xml)\n* 高级分析与R http:\u002F\u002Fadvanceddataanalytics.net\u002F [(RSS)](http:\u002F\u002Fadvanceddataanalytics.net\u002Ffeed\u002F)\n* 数据之地探险 http:\u002F\u002Fblog.smola.org [(RSS)](http:\u002F\u002Fblog.smola.org\u002Frss)\n* 敏捷数据科学 http:\u002F\u002Fblog.sense.io\u002F [(RSS)](http:\u002F\u002Fblog.sense.io\u002Frss\u002F)\n* Ahmed El Deeb https:\u002F\u002Fmedium.com\u002F@D33B [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@D33B)\n* Airbnb 数据博客 http:\u002F\u002Fnerds.airbnb.com\u002Fdata\u002F [(RSS)](http:\u002F\u002Fnerds.airbnb.com\u002Ffeed\u002F)\n* Alex Castrounis | InnoArchiTech http:\u002F\u002Fwww.innoarchitech.com\u002F [(RSS)](http:\u002F\u002Fwww.innoarchitech.com\u002Ffeed.xml)\n* Alex Perrier http:\u002F\u002Falexperrier.github.io\u002F [(RSS)](http:\u002F\u002Falexperrier.github.io\u002Ffeed.xml)\n* Algobeans | 面向普通人的数据分析教程与实验 https:\u002F\u002Falgobeans.com [(RSS)](https:\u002F\u002Falgobeans.com\u002Ffeed\u002F)\n* 亚马逊AWS AI博客 https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Fai\u002F [(RSS)](https:\u002F\u002Faws.amazon.com\u002Fblogs\u002Famazon-ai\u002Ffeed\u002F)\n* Analytics Vidhya http:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FAnalyticsVidhya)\n* Sicara 的大数据分析与可视化 https:\u002F\u002Fblog.sicara.com [(RSS)](https:\u002F\u002Fblog.sicara.com\u002Ffeed)\n* Andreas Müller http:\u002F\u002Fpeekaboo-vision.blogspot.com\u002F [(RSS)](http:\u002F\u002Fpeekaboo-vision.blogspot.com\u002Fatom.xml)\n* Andrej Karpathy 博客 http:\u002F\u002Fkarpathy.github.io\u002F [(RSS)](http:\u002F\u002Fkarpathy.github.io\u002Ffeed.xml)\n* Andrew Brooks http:\u002F\u002Fbrooksandrew.github.io\u002Fsimpleblog\u002F [(RSS)](http:\u002F\u002Fbrooksandrew.github.io\u002Fsimpleblog\u002Ffeed.xml)\n* Andrey Kurenkov http:\u002F\u002Fwww.andreykurenkov.com\u002Fwriting\u002F [(RSS)](http:\u002F\u002Fwww.andreykurenkov.com\u002Fwriting\u002Ffeed.xml\u002F)\n* Anton Lebedevich 的博客 http:\u002F\u002Fmabrek.github.io\u002F [(RSS)](http:\u002F\u002Fmabrek.github.io\u002Ffeed.xml)\n* Arthur Juliani https:\u002F\u002Fmedium.com\u002F@awjuliani [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@awjuliani)\n* Audun M. Øygard http:\u002F\u002Fwww.auduno.com\u002F [(RSS)](http:\u002F\u002Fauduno.tumblr.com\u002Frss)\n* Avi Singh https:\u002F\u002Favisingh599.github.io\u002F [(RSS)](http:\u002F\u002Favisingh599.github.io\u002Ffeed.xml)\n* 美丽的数据 http:\u002F\u002Fbeautifuldata.net\u002F [(RSS)](http:\u002F\u002Fbeautifuldata.net\u002Ffeed\u002F)\n* Beckerfuffle http:\u002F\u002Fmdbecker.github.io\u002F [(RSS)](http:\u002F\u002Fmdbecker.github.io\u002Fatom.xml)\n* 成为数据科学家 http:\u002F\u002Fwww.becomingadatascientist.com\u002F [(RSS)](http:\u002F\u002Fwww.becomingadatascientist.com\u002Ffeed\u002F)\n* Ben Bolte 的博客 http:\u002F\u002Fbenjaminbolte.com\u002Fml\u002F [(RSS)](http:\u002F\u002Fbenjaminbolte.com\u002Fml\u002F)\n* Ben Frederickson http:\u002F\u002Fwww.benfrederickson.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.benfrederickson.com\u002Fatom.xml)\n* 伯克利人工智能研究 http:\u002F\u002Fbair.berkeley.edu\u002Fblog\u002F [(RSS)](http:\u002F\u002Fbair.berkeley.edu\u002Fblog\u002Ffeed.xml)\n* 大型数据 http:\u002F\u002Fbigishdata.com\u002F [(RSS)](http:\u002F\u002Fbigishdata.com\u002Ffeed\u002F)\n* 神经网络博客 http:\u002F\u002Fyerevann.github.io\u002F [(RSS)](http:\u002F\u002Fyerevann.github.io\u002Fatom.xml)\n* 回归项目博客 http:\u002F\u002Fd10genes.github.io\u002Fblog\u002F [(RSS)](http:\u002F\u002Fd10genes.github.io\u002Fblog\u002Ffeed.xml)\n* blogR | 科学家分享的R语言技巧 https:\u002F\u002Fdrsimonj.svbtle.com\u002F [(RSS)](https:\u002F\u002Fdrsimonj.svbtle.com\u002F)\n* mat kelcey 的大脑 http:\u002F\u002Fmatpalm.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmatpalm.com\u002Fblog\u002Ffeed)\n* 关于科学和编程的精彩错误思考 https:\u002F\u002Farogozhnikov.github.io\u002F [(RSS)](http:\u002F\u002Farogozhnikov.github.io\u002Ffeed.xml)\n* Bugra Akyildiz http:\u002F\u002Fbugra.github.io\u002F [(RSS)](http:\u002F\u002Fbugra.github.io\u002Ffeeds\u002Fall.atom.xml)\n* 建造巴别塔 https:\u002F\u002Fbuilding-babylon.net\u002F [(RSS)](http:\u002F\u002Fbuilding-babylon.net\u002Ffeed\u002F)\n* Carl Shan http:\u002F\u002Fcarlshan.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fcarlshan)\n* Chris Stucchio https:\u002F\u002Fwww.chrisstucchio.com\u002Fblog\u002Findex.html [(RSS)](http:\u002F\u002Fwww.chrisstucchio.com\u002Fblog\u002Fatom.xml)\n* Christophe Bourguignat https:\u002F\u002Fmedium.com\u002F@chris_bour [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@chris_bour)\n* Christopher Nguyen https:\u002F\u002Fmedium.com\u002F@ctn [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@ctn)\n* Cloudera 数据科学文章 http:\u002F\u002Fblog.cloudera.com\u002Fblog\u002Fcategory\u002Fdata-science\u002F [(RSS)](http:\u002F\u002Fblog.cloudera.com\u002Fblog\u002Fcategory\u002Fdata-science\u002Ffeed\u002F)\n* colah 的博客 http:\u002F\u002Fcolah.github.io\u002Farchive.html [(RSS)](http:\u002F\u002Fcolah.github.io\u002Frss.xml)\n* Cortana 智能与机器学习博客 https:\u002F\u002Fblogs.technet.microsoft.com\u002Fmachinelearning\u002F [(RSS)](http:\u002F\u002Fblogs.technet.com\u002Fb\u002Fmachinelearning\u002Frss.aspx)\n* Daniel Forsyth http:\u002F\u002Fwww.danielforsyth.me\u002F [(RSS)](http:\u002F\u002Fwww.danielforsyth.me\u002Frss\u002F)\n* Daniel Homola http:\u002F\u002Fdanielhomola.com\u002Fcategory\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdanielhomola.com\u002Ffeed\u002F)\n* Daniel Nee http:\u002F\u002Fdanielnee.com [(RSS)](http:\u002F\u002Fdanielnee.com\u002F?feed=rss2)\n* 基于数据的发明 http:\u002F\u002Fdatalab.lu\u002F [(RSS)](http:\u002F\u002Fdatalab.lu\u002Fatom.xml)\n* 数据博主 https:\u002F\u002Fwww.data-blogger.com\u002F [(RSS)](https:\u002F\u002Fwww.data-blogger.com\u002Ffeed\u002F)\n* Data Labs http:\u002F\u002Fblog.insightdatalabs.com\u002F [(RSS)](http:\u002F\u002Fblog.insightdatalabs.com\u002Frss\u002F)\n* 数据与媒体 http:\u002F\u002Fdatameetsmedia.com\u002F [(RSS)](http:\u002F\u002Fdatameetsmedia.com\u002Ffeed\u002F)\n* 数据挖掘者博客 http:\u002F\u002Fblog.data-miners.com\u002F [(RSS)](http:\u002F\u002Fblog.data-miners.com\u002Ffeeds\u002Fposts\u002Fdefault?alt=rss)\n* 数据挖掘研究 http:\u002F\u002Fwww.dataminingblog.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fdataminingblog)\n* 数据挖掘：文本挖掘、可视化与社交媒体 http:\u002F\u002Fdatamining.typepad.com\u002Fdata_mining\u002F [(RSS)](http:\u002F\u002Fdatamining.typepad.com\u002Fdata_mining\u002Fatom.xml)\n* Data Piques http:\u002F\u002Fblog.ethanrosenthal.com\u002F [(RSS)](http:\u002F\u002Fblog.ethanrosenthal.com\u002Ffeeds\u002Fall.atom.xml)\n* 数据学校 http:\u002F\u002Fwww.dataschool.io\u002F [(RSS)](http:\u002F\u002Fwww.dataschool.io\u002Frss\u002F)\n* 数据科学入门 http:\u002F\u002F101.datascience.community\u002F [(RSS)](http:\u002F\u002F101.datascience.community\u002Ffeed\u002F)\n* Facebook 的数据科学 https:\u002F\u002Fresearch.facebook.com\u002Fblog\u002Fdatascience\u002F [(RSS)](https:\u002F\u002Fresearch.facebook.com\u002Fblog\u002Fdatascience\u002F)\n* 数据科学洞察 http:\u002F\u002Fwww.datasciencebowl.com\u002Fdata-science-insights\u002F [(RSS)](http:\u002F\u002Fwww.datasciencebowl.com\u002Ffeed\u002F)\n* 数据科学教程 https:\u002F\u002Fcodementor.io\u002Fdata-science\u002Ftutorial [(RSS)](https:\u002F\u002Fwww.codementor.io\u002Fdata-science\u002Ftutorial\u002Ffeed)\n* 数据科学指南 http:\u002F\u002Fdatasciencevademecum.wordpress.com\u002F [(RSS)](http:\u002F\u002Fdatasciencevademecum.wordpress.com\u002Ffeed\u002F)\n* Dataaspirant http:\u002F\u002Fdataaspirant.com\u002F [(RSS)](http:\u002F\u002Fdataaspirant.wordpress.com\u002Ffeed\u002F)\n* Dataclysm http:\u002F\u002Fblog.okcupid.com\u002F [(RSS)](http:\u002F\u002Fblog.okcupid.com\u002Findex.php\u002Ffeed\u002F)\n* DataGenetics http:\u002F\u002Fdatagenetics.com\u002Fblog.html [(RSS)](http:\u002F\u002Fdatagenetics.com\u002Ffeed\u002Frss.xml)\n* Dataiku https:\u002F\u002Fwww.dataiku.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.dataiku.com\u002Ffeed.xml)\n* DataKind http:\u002F\u002Fwww.datakind.org\u002Fblog [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FDataKin)\n* DataLook http:\u002F\u002Fblog.datalook.io\u002F [(RSS)](http:\u002F\u002Fblog.datalook.io\u002Ffeed\u002F)\n* Datanice https:\u002F\u002Fdatanice.wordpress.com\u002F [(RSS)](https:\u002F\u002Fdatanice.wordpress.com\u002Ffeed\u002F)\n* Dataquest 博客 https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002F [(RSS)](https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002Fatom.xml)\n* DataRobot http:\u002F\u002Fwww.datarobot.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.datarobot.com\u002Ffeed\u002F)\n* Datascope http:\u002F\u002Fdatascopeanalytics.com\u002Fblog [(RSS)](http:\u002F\u002Fdatascopeanalytics.com\u002Frss)\n* DatasFrame http:\u002F\u002Ftomaugspurger.github.io\u002F [(RSS)](http:\u002F\u002Ftomaugspurger.github.io\u002Ffeeds\u002Fall.rss.xml)\n* David Mimno http:\u002F\u002Fwww.mimno.org\u002F [(RSS)](http:\u002F\u002Fmimno.infosci.cornell.edu\u002Fb\u002Ffeed.xml)\n* Dayne Batten http:\u002F\u002Fdaynebatten.com [(RSS)](http:\u002F\u002Fdaynebatten.com\u002Ffeed\u002F)\n* 深度学习 http:\u002F\u002Fdeeplearning.net\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdeeplearning.net\u002Ffeed\u002F)\n* Deepdish http:\u002F\u002Fdeepdish.io\u002F [(RSS)](http:\u002F\u002Fdeepdish.io\u002Fatom.xml)\n* Delip Rao http:\u002F\u002Fdeliprao.com\u002F [(RSS)](http:\u002F\u002Fdeliprao.com\u002Ffeed)\n* DENNY 的博客 http:\u002F\u002Fblog.dennybritz.com\u002F [(RSS)](http:\u002F\u002Fblog.dennybritz.com\u002Ffeed\u002F)\n* Dimensionless https:\u002F\u002Fdimensionless.in\u002Fblog\u002F [(RSS)](https:\u002F\u002Fdimensionless.in\u002Ffeed)\n* Distill http:\u002F\u002Fdistill.pub\u002F [(RSS)](http:\u002F\u002Fdistill.pub\u002Frss.xml)\n* District Data Labs http:\u002F\u002Fdistrictdatalabs.silvrback.com\u002F [(RSS)](https:\u002F\u002Fdistrictdatalabs.silvrback.com\u002Ffeed)\n* 潜入数据 https:\u002F\u002Fblog.datadive.net\u002F [(RSS)](http:\u002F\u002Fblog.datadive.net\u002Ffeed\u002F)\n* Domino 数据实验室博客 http:\u002F\u002Fblog.dominodatalab.com\u002F [(RSS)](http:\u002F\u002Fblog.dominodatalab.com\u002Frss\u002F)\n* Randal S. Olson 博士 http:\u002F\u002Fwww.randalolson.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.randalolson.com\u002Ffeed\u002F)\n* Drew Conway https:\u002F\u002Fmedium.com\u002F@drewconway [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@drewconway)\n* Dustin Tran http:\u002F\u002Fdustintran.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdustintran.com\u002Fblog\u002Frss\u002F)\n* Eder Santana https:\u002F\u002Federsantana.github.io\u002Fblog.html [(RSS)](http:\u002F\u002Federsantana.github.io\u002Ffeed.xml)\n* Edwin Chen http:\u002F\u002Fblog.echen.me [(RSS)](http:\u002F\u002Fblog.echen.me\u002Ffeeds\u002Fall.rss.xml)\n* EFavDB http:\u002F\u002Fefavdb.com\u002F [(RSS)](http:\u002F\u002Fefavdb.com\u002Ffeed\u002F)\n* Emilio Ferrara, Ph.D.  http:\u002F\u002Fwww.emilio.ferrara.name\u002F [(RSS)](http:\u002F\u002Fwww.emilio.ferrara.name\u002Ffeed\u002F)\n* 创业极客精神 http:\u002F\u002Fianozsvald.com\u002F [(RSS)](http:\u002F\u002Fianozsvald.com\u002Ffeed\u002F)\n* Eric Jonas http:\u002F\u002Fericjonas.com\u002Farchives.html [(RSS)](http:\u002F\u002Fericjonas.com\u002Farchives.html)\n* Eric Siegel http:\u002F\u002Fwww.predictiveanalyticsworld.com\u002Fblog [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fpredictiveanalyticsworld\u002FGXRy)\n* Erik Bern http:\u002F\u002Ferikbern.com [(RSS)](http:\u002F\u002Ferikbern.com\u002Ffeed\u002F)\n* ERIN SHELLMAN http:\u002F\u002Fwww.erinshellman.com\u002F [(RSS)](http:\u002F\u002Fwww.erinshellman.com\u002Ffeed\u002F)\n* Eugenio Culurciello http:\u002F\u002Fculurciello.github.io\u002F [(RSS)](http:\u002F\u002Fculurciello.github.io\u002Ffeed.xml)\n* Fabian Pedregosa http:\u002F\u002Ffa.bianp.net\u002F [(RSS)](http:\u002F\u002Ffa.bianp.net\u002Fblog\u002Ffeed\u002F)\n* Fast Forward Labs http:\u002F\u002Fblog.fastforwardlabs.com\u002F [(RSS)](http:\u002F\u002Fblog.fastforwardlabs.com\u002Frss)\n* FastML http:\u002F\u002Ffastml.com\u002F [(RSS)](http:\u002F\u002Ffastml.com\u002Fatom.xml)\n* Florian Hartl http:\u002F\u002Fflorianhartl.com\u002F [(RSS)](http:\u002F\u002Fflorianhartl.com\u002Ffeed\u002F)\n* FlowingData http:\u002F\u002Fflowingdata.com\u002F [(RSS)](http:\u002F\u002Fflowingdata.com\u002Ffeed\u002F)\n* 全栈机器学习 http:\u002F\u002Ffullstackml.com\u002F [(RSS)](http:\u002F\u002Ffullstackml.com\u002Ffeed\u002F)\n* GAB41 http:\u002F\u002Fwww.lab41.org\u002Fgab41\u002F [(RSS)](http:\u002F\u002Fwww.lab41.org\u002Ffeed\u002F)\n* Garbled Notes http:\u002F\u002Fwww.chioka.in\u002F [(RSS)](http:\u002F\u002Fwww.chioka.in\u002Ffeed.xml)\n* Greg Reda http:\u002F\u002Fwww.gregreda.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.gregreda.com\u002Ffeeds\u002Fall.atom.xml)\n* Hyon S Chu https:\u002F\u002Fmedium.com\u002F@adailyventure [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@adailyventure)\n* i am trask http:\u002F\u002Fiamtrask.github.io\u002F [(RSS)](http:\u002F\u002Fiamtrask.github.io\u002Ffeed.xml)\n* I Quant NY http:\u002F\u002Fiquantny.tumblr.com\u002F [(RSS)](http:\u002F\u002Fiquantny.tumblr.com\u002Frss)\n* inFERENCe http:\u002F\u002Fwww.inference.vc\u002F [(RSS)](http:\u002F\u002Fwww.inference.vc\u002Frss\u002F)\n* Insight 数据科学 https:\u002F\u002Fblog.insightdatascience.com\u002F [(RSS)](https:\u002F\u002Fblog.insightdatascience.com\u002Ffeed)\n* 灵感信息 http:\u002F\u002Fmyinspirationinformation.com\u002F [(RSS)](http:\u002F\u002Fmyinspirationinformation.com\u002Ffeed\u002F)\n* Ira Korshunova http:\u002F\u002Firakorshunova.github.io\u002F [(RSS)](http:\u002F\u002Firakorshunova.github.io\u002Ffeed.xml)\n* 我是强盗 https:\u002F\u002Fblogs.princeton.edu\u002Fimabandit\u002F [(RSS)](https:\u002F\u002Fblogs.princeton.edu\u002Fimabandit\u002Ffeed\u002F)\n* Jason Toy http:\u002F\u002Fwww.jtoy.net\u002F [(RSS)](http:\u002F\u002Fjtoy.net\u002Fatom.xml)\n* Jeremy D. Jackson, PhD http:\u002F\u002Fwww.jeremydjacksonphd.com\u002F [(RSS)](http:\u002F\u002Fwww.jeremydjacksonphd.com\u002F?feed=rss2)\n* Jesse Steinweg-Woods https:\u002F\u002Fjessesw.com\u002F [(RSS)](https:\u002F\u002Fjessesw.com\u002Ffeed.xml)\n* Joe Cauteruccio http:\u002F\u002Fwww.joecjr.com\u002F [(RSS)](http:\u002F\u002Fwww.joecjr.com\u002Ffeed\u002F)\n* John Myles White http:\u002F\u002Fwww.johnmyleswhite.com\u002F [(RSS)](http:\u002F\u002Fwww.johnmyleswhite.com\u002Ffeed\u002F)\n* John 的肥皂箱 http:\u002F\u002Fjoschu.github.io\u002F [(RSS)](http:\u002F\u002Fjoschu.github.io\u002Ffeed.xml)\n* Jonas Degrave http:\u002F\u002F317070.github.io\u002F [(RSS)](http:\u002F\u002F317070.github.io\u002Ffeed.xml)\n* 数据之乐 http:\u002F\u002Fwww.joyofdata.de\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.joyofdata.de\u002Fblog\u002Ffeed\u002F)\n* Julia Evans http:\u002F\u002Fjvns.ca\u002F [(RSS)](http:\u002F\u002Fjvns.ca\u002Fatom.xml)\n* KDnuggets http:\u002F\u002Fwww.kdnuggets.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fkdnuggets-data-mining-analytics)\n* 跟上最新技术 http:\u002F\u002Fcolinpriest.com\u002F [(RSS)](http:\u002F\u002Fcolinpriest.com\u002Ffeed\u002F)\n* Kenny Bastani http:\u002F\u002Fwww.kennybastani.com\u002F [(RSS)](http:\u002F\u002Fwww.kennybastani.com\u002Ffeeds\u002Fposts\u002Fdefault?alt=rss)\n* Kevin Davenport http:\u002F\u002Fkldavenport.com\u002F [(RSS)](http:\u002F\u002Fkldavenport.com\u002Ffeed\u002F)\n* kevin frans http:\u002F\u002Fkvfrans.com\u002F [(RSS)](http:\u002F\u002Fkvfrans.com\u002Frss\u002F)\n* korbonits | 数学 ∩ 数据 http:\u002F\u002Fkorbonits.github.io\u002F [(RSS)](http:\u002F\u002Fkorbonits.github.io\u002Ffeed.xml)\n* 大规模机器学习 http:\u002F\u002Fbickson.blogspot.com\u002F [(RSS)](http:\u002F\u002Fbickson.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* LATERAL 博客 https:\u002F\u002Fblog.lateral.io\u002F [(RSS)](https:\u002F\u002Fblog.lateral.io\u002Ffeed\u002F)\n* Lazy Programmer http:\u002F\u002Flazyprogrammer.me\u002F [(RSS)](http:\u002F\u002Flazyprogrammer.me\u002Ffeed\u002F)\n* 在这里学习分析 https:\u002F\u002Flearnanalyticshere.wordpress.com\u002F [(RSS)](https:\u002F\u002Flearnanalyticshere.wordpress.com\u002Ffeed\u002F)\n* LearnDataSci http:\u002F\u002Fwww.learndatasci.com\u002F [(RSS)](http:\u002F\u002Fwww.learndatasci.com\u002Ffeed\u002F)\n* 通过数据学习 http:\u002F\u002Flearningwithdata.com\u002F [(RSS)](http:\u002F\u002Flearningwithdata.com\u002Frss_feed.xml)\n* 生活、语言、学习 http:\u002F\u002Fdaoudclarke.github.io\u002F [(RSS)](http:\u002F\u002Fdaoudclarke.github.io\u002Fatom.xml)\n* Locke 数据 https:\u002F\u002Fitsalocke.com\u002Fblog\u002F [(RSS)](https:\u002F\u002Fitsalocke.com\u002Ffeed)\n* Louis Dorard http:\u002F\u002Fwww.louisdorard.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.louisdorard.com\u002Fblog?format=rss)\n* M.E.Driscoll http:\u002F\u002Fmedriscoll.com\u002F [(RSS)](http:\u002F\u002Fmedriscoll.com\u002Frss)\n* Machinalis http:\u002F\u002Fwww.machinalis.com\u002Fblog [(RSS)](http:\u002F\u002Fwww.machinalis.com\u002Fblog\u002Ffeeds\u002Frss\u002F)\n* 机器学习（理论） http:\u002F\u002Fhunch.net\u002F [(RSS)](http:\u002F\u002Fhunch.net\u002F?feed=rss2)\n* 机器学习与数据科学 http:\u002F\u002Falexhwoods.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Falexhwoods.com\u002Ffeed\u002F)\n* 机器学习 https:\u002F\u002Fcharlesmartin14.wordpress.com\u002F [(RSS)](http:\u002F\u002Fcharlesmartin14.wordpress.com\u002Ffeed\u002F)\n* 机器学习精通 http:\u002F\u002Fmachinelearningmastery.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmachinelearningmastery.com\u002Ffeed\u002F)\n* 机器学习博客 https:\u002F\u002Fmachinelearningblogs.com\u002F [(RSS)](https:\u002F\u002Fmachinelearningblogs.com\u002Ffeed\u002F)\n* 机器学习等 http:\u002F\u002Fyaroslavvb.blogspot.com [(RSS)](http:\u002F\u002Fyaroslavvb.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* 机器学习、数学和物理 https:\u002F\u002Fmlopezm.wordpress.com\u002F [(RSS)](https:\u002F\u002Fmlopezm.wordpress.com\u002Ffeed\u002F)\n* 机器学习抽认卡 https:\u002F\u002Fmachinelearningflashcards.com\u002F 10美元，一套精美插画的300张抽认卡\n* Machined Learnings http:\u002F\u002Fwww.machinedlearnings.com\u002F [(RSS)](http:\u002F\u002Fwww.machinedlearnings.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* 映射巴别塔 https:\u002F\u002Fjack-clark.net\u002F [(RSS)](https:\u002F\u002Fjack-clark.net\u002Ffeed\u002F)\n* MAPR 博客 https:\u002F\u002Fwww.mapr.com\u002Fblog [(RSS)](https:\u002F\u002Fwww.mapr.com\u002Fbigdata.xml)\n* MAREK REI http:\u002F\u002Fwww.marekrei.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.marekrei.com\u002Fblog\u002Ffeed\u002F)\n* 有点意思 http:\u002F\u002Fblog.mikiobraun.de\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FMarginallyInteresting)\n* 数学 ∩ 编程 http:\u002F\u002Fjeremykun.com\u002F [(RSS)](http:\u002F\u002Fjeremykun.wordpress.com\u002Ffeed\u002F)\n* Matthew Rocklin http:\u002F\u002Fmatthewrocklin.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmatthewrocklin.com\u002Fblog\u002Fatom.xml)\n* Melody Wolk http:\u002F\u002Fmelodywolk.com\u002Fprojects\u002F [(RSS)](http:\u002F\u002Fmelodywolk.com\u002Ffeed\u002F)\n* Mic Farris http:\u002F\u002Fwww.micfarris.com\u002F [(RSS)](http:\u002F\u002Fwww.micfarris.com\u002Ffeed\u002F)\n* Mike Tyka http:\u002F\u002Fmtyka.github.io\u002F [(RSS)](http:\u002F\u002Fmtyka.github.io\u002F\u002Ffeed.xml)\n* minimaxir | Max Woolf 的博客 http:\u002F\u002Fminimaxir.com\u002F [(RSS)](http:\u002F\u002Fminimaxir.com\u002Frss.xml)\n* 镜像图像 https:\u002F\u002Fmirror2image.wordpress.com\u002F [(RSS)](http:\u002F\u002Fmirror2image.wordpress.com\u002Ffeed\u002F)\n* Mitch Crowe http:\u002F\u002Fwww.dataphoric.com\u002F [(RSS)](http:\u002F\u002Fwww.dataphoric.com\u002Ffeed.xml)\n* MLWave http:\u002F\u002Fmlwave.com\u002F [(RSS)](http:\u002F\u002Fmlwave.com\u002Ffeed\u002F)\n* MLWhiz http:\u002F\u002Fmlwhiz.com\u002F [(RSS)](http:\u002F\u002Fmlwhiz.com\u002Fatom.xml)\n* 模型既启发又错误 https:\u002F\u002Fpeadarcoyle.wordpress.com\u002F [(RSS)](http:\u002F\u002Fpeadarcoyle.wordpress.com\u002Ffeed\u002F)\n* Moody Rd http:\u002F\u002Fblog.mrtz.org\u002F [(RSS)](http:\u002F\u002Fblog.mrtz.org\u002Ffeed.xml)\n* 月球计划 http:\u002F\u002Fjxieeducation.com\u002F [(RSS)](http:\u002F\u002Fjxieeducation.com\u002Ffeed.xml)\n* Mourad Mourafiq http:\u002F\u002Fmourafiq.com\u002F [(RSS)](http:\u002F\u002Fmourafiq.com\u002Fatom.xml)\n* 我对数据科学、预测分析和Python的看法 http:\u002F\u002Fshahramabyari.com\u002F [(RSS)](http:\u002F\u002Fshahramabyari.com\u002Ffeed\u002F)\n* 自然语言处理博客 http:\u002F\u002Fnlpers.blogspot.fr\u002F [(RSS)](http:\u002F\u002Fnlpers.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Neil Lawrence http:\u002F\u002Finverseprobability.com\u002Fblog.html [(RSS)](http:\u002F\u002Finverseprobability.com\u002Frss.xml)\n* NLP和深度学习爱好者 http:\u002F\u002Fcamron.xyz\u002F [(RSS)](http:\u002F\u002Fcamron.xyz\u002Findex.php\u002Ffeed\u002F)\n* 没有免费的直觉 http:\u002F\u002Fblog.kaggle.com\u002F [(RSS)](http:\u002F\u002Fblog.kaggle.com\u002Ffeed\u002F)\n* 白夜 http:\u002F\u002Fnuit-blanche.blogspot.com\u002F [(RSS)](http:\u002F\u002Fnuit-blanche.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* 数字2147483647 https:\u002F\u002Fno2147483647.wordpress.com\u002F [(RSS)](http:\u002F\u002Fno2147483647.wordpress.com\u002Ffeed\u002F)\n* 关于机器智能 https:\u002F\u002Faimatters.wordpress.com\u002F [(RSS)](https:\u002F\u002Faimatters.wordpress.com\u002Ffeed\u002F)\n* 大众的鸦片 数据就是我们的宗教。http:\u002F\u002Fopiateforthemass.es\u002F [(RSS)](http:\u002F\u002Fopiateforthemass.es\u002Ffeed.xml)\n* p-value.info http:\u002F\u002Fwww.p-value.info\u002F [(RSS)](http:\u002F\u002Fwww.p-value.info\u002Ffeeds\u002Fposts\u002Fdefault)\n* Pete Warden 的博客 http:\u002F\u002Fpetewarden.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Ftypepad\u002Fpetewarden)\n* Plotly 博客 http:\u002F\u002Fblog.plot.ly\u002F [(RSS)](http:\u002F\u002Fblog.plot.ly\u002Frss)\n* 可能想得太多了 http:\u002F\u002Fallendowney.blogspot.ca\u002F [(RSS)](http:\u002F\u002Fallendowney.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Prooffreader.com http:\u002F\u002Fwww.prooffreader.com [(RSS)](http:\u002F\u002Fwww.prooffreader.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* ProoffreaderPlus http:\u002F\u002Fprooffreaderplus.blogspot.ca\u002F [(RSS)](http:\u002F\u002Fprooffreaderplus.blogspot.ca\u002Ffeeds\u002Fposts\u002Fdefault)\n* 可发表的内容 http:\u002F\u002Fwww.sumsar.net\u002F [(RSS)](http:\u002F\u002Fwww.sumsar.net\u002Fatom.xml)\n* PyImageSearch http:\u002F\u002Fwww.pyimagesearch.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FPyimagesearch)\n* Python式的漫游 https:\u002F\u002Fjakevdp.github.io\u002F [(RSS)](http:\u002F\u002Fjakevdp.github.com\u002Fatom.xml)\n* quintuitive http:\u002F\u002Fquintuitive.com\u002F [(RSS)](http:\u002F\u002Fquintuitive.com\u002Ffeed\u002F)\n* R语言与数据挖掘 https:\u002F\u002Frdatamining.wordpress.com\u002F [(RSS)](http:\u002F\u002Frdatamining.wordpress.com\u002Ffeed\u002F)\n* R-bloggers http:\u002F\u002Fwww.r-bloggers.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FRBloggers)\n* R2RT http:\u002F\u002Fr2rt.com\u002F [(RSS)](http:\u002F\u002Fr2rt.com\u002Ffeeds\u002Fall.atom.xml)\n* Ramiro Gómez http:\u002F\u002Framiro.org\u002Fnotebooks\u002F [(RSS)](http:\u002F\u002Framiro.org\u002Fnotebook\u002Frss.xml)\n* 关于计算机科学、数学和软件工程的随机笔记 http:\u002F\u002Fbarmaley-exe.github.io\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fbarmaley-exe-blog-feed)\n* Randy Zwitch http:\u002F\u002Frandyzwitch.com\u002F [(RSS)](http:\u002F\u002Frandyzwitch.com\u002Ffeed.xml)\n* RaRe Technologies http:\u002F\u002Frare-technologies.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Frare-technologies.com\u002Ffeed\u002F)\n* Rayli.Net http:\u002F\u002Frayli.net\u002Fblog\u002F [(RSS)](http:\u002F\u002Frayli.net\u002Fblog\u002Ffeed\u002F)\n* Revolutions http:\u002F\u002Fblog.revolutionanalytics.com\u002F [(RSS)](http:\u002F\u002Fblog.revolutionanalytics.com\u002Fatom.xml)\n* Rinu Boney http:\u002F\u002Frinuboney.github.io\u002F [(RSS)](http:\u002F\u002Frinuboney.github.io\u002Ffeed.xml)\n* RNDuja 博客 http:\u002F\u002Frnduja.github.io\u002F [(RSS)](http:\u002F\u002Frnduja.github.io\u002Ffeed.xml)\n* Robert Chang https:\u002F\u002Fmedium.com\u002F@rchang [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@rchang)\n* 火箭动力数据科学 http:\u002F\u002Frocketdatascience.org [(RSS)](http:\u002F\u002Frocketdatascience.org\u002F?feed=rss2)\n* Sachin Joglekar 的博客 https:\u002F\u002Fcodesachin.wordpress.com\u002F [(RSS)](https:\u002F\u002Fcodesachin.wordpress.com\u002Ffeed\u002F)\n* samim https:\u002F\u002Fmedium.com\u002F@samim [(RSS)](https:\u002F\u002Fmedium.com\u002Ffeed\u002F@samim)\n* Sean J. Taylor http:\u002F\u002Fseanjtaylor.com\u002F [(RSS)](http:\u002F\u002Fseanjtaylor.com\u002Frss)\n* Sebastian Raschka http:\u002F\u002Fsebastianraschka.com\u002Fblog\u002Findex.html [(RSS)](http:\u002F\u002Fsebastianraschka.com\u002Frss_feed.xml)\n* Sebastian Ruder http:\u002F\u002Fsebastianruder.com\u002F [(RSS)](http:\u002F\u002Fsebastianruder.com\u002Frss\u002F)\n* Sebastian 的慢博客 http:\u002F\u002Fwww.nowozin.net\u002Fsebastian\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.nowozin.net\u002Fsebastian\u002Fblog\u002Ffeeds\u002Fall.atom.xml)\n* SFL 科学博客 https:\u002F\u002Fsflscientific.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fsflscientific.com\u002Fblog\u002F?format=rss)\n* Shakir 的机器学习博客 http:\u002F\u002Fblog.shakirm.com\u002F [(RSS)](http:\u002F\u002Fblog.shakirm.com\u002Ffeed\u002F)\n* 简单统计 http:\u002F\u002Fsimplystatistics.org [(RSS)](http:\u002F\u002Fsimplystatistics.org\u002Ffeed\u002F)\n* Springboard 博客 http:\u002F\u002Fspringboard.com\u002Fblog\n* Startup.ML 博客 http:\u002F\u002Fstartup.ml\u002Fblog [(RSS)](http:\u002F\u002Fwww.startup.ml\u002Fblog?format=RSS)\n* 统计建模、因果推断和社会科学 http:\u002F\u002Fandrewgelman.com\u002F [(RSS)](http:\u002F\u002Fandrewgelman.com\u002Ffeed\u002F)\n* 斯蒂格勒饮食 http:\u002F\u002Fstiglerdiet.com\u002F [(RSS)](http:\u002F\u002Fstiglerdiet.com\u002Ffeeds\u002Fall.atom.xml)\n* Stitch Fix 技术博客 http:\u002F\u002Fmultithreaded.stitchfix.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fmultithreaded.stitchfix.com\u002Ffeed.xml)\n* 随机研发笔记 http:\u002F\u002Farseny.info\u002F [(RSS)](http:\u002F\u002Farseny.info\u002Ffeeds\u002Fall.rss.xml)\n* Quora 上用统计讲故事 http:\u002F\u002Fdatastories.quora.com\u002F [(RSS)](http:\u002F\u002Fdatastories.quora.com\u002Frss)\n* StreamHacker http:\u002F\u002Fstreamhacker.com\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002FStreamHacker)\n* 下意识的随想 http:\u002F\u002Fblogs.sas.com\u002Fcontent\u002Fsubconsciousmusings\u002F [(RSS)](http:\u002F\u002Ffeeds.feedburner.com\u002Fadvanalytics)\n* Swan Intelligence http:\u002F\u002Fswanintelligence.com\u002F [(RSS)](http:\u002F\u002Fswanintelligence.com\u002Ffeeds\u002Fall.rss.xml)\n* TechnoCalifornia http:\u002F\u002Ftechnocalifornia.blogspot.se\u002F [(RSS)](http:\u002F\u002Ftechnocalifornia.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* 文本分析博客 | AYLIEN http:\u002F\u002Fblog.aylien.com\u002F [(RSS)](http:\u002F\u002Fblog.aylien.com\u002Frss)\n* 愤怒的统计学家 http:\u002F\u002Fangrystatistician.blogspot.com\u002F [(RSS)](http:\u002F\u002Fangrystatistician.blogspot.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* 聪明的机器 https:\u002F\u002Ftheclevermachine.wordpress.com\u002F [(RSS)](http:\u002F\u002Ftheclevermachine.wordpress.com\u002Ffeed\u002F)\n* 数据营博客 https:\u002F\u002Fwww.datacamp.com\u002Fcommunity\u002Fblog [(RSS)](http:\u002F\u002Fblog.datacamp.com\u002Ffeed\u002F)\n* 数据孵化器 http:\u002F\u002Fblog.thedataincubator.com\u002F [(RSS)](http:\u002F\u002Fblog.thedataincubator.com\u002Ffeed\u002F)\n* 数据科学实验室 https:\u002F\u002Fdatasciencelab.wordpress.com\u002F [(RSS)](http:\u002F\u002Fdatasciencelab.wordpress.com\u002Ffeed\u002F)\n* THE ETZ-FILES http:\u002F\u002Falexanderetz.com\u002F [(RSS)](http:\u002F\u002Fnicebrain.wordpress.com\u002Ffeed\u002F)\n* 数据科学 http:\u002F\u002Fwww.martingoodson.com [(RSS)](http:\u002F\u002Fwww.martingoodson.com\u002Frss\u002F)\n* 数据的形状 https:\u002F\u002Fshapeofdata.wordpress.com [(RSS)](https:\u002F\u002Fshapeofdata.wordpress.com\u002Ffeed\u002F)\n* 非官方谷歌数据科学博客 http:\u002F\u002Fwww.unofficialgoogledatascience.com\u002F [(RSS)](http:\u002F\u002Fwww.unofficialgoogledatascience.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Tim Dettmers http:\u002F\u002Ftimdettmers.com\u002F [(RSS)](http:\u002F\u002Ftimdettmers.com\u002Ffeed\u002F)\n* Tombone 的计算机视觉博客 http:\u002F\u002Fwww.computervisionblog.com\u002F [(RSS)](http:\u002F\u002Fwww.computervisionblog.com\u002Ffeeds\u002Fposts\u002Fdefault)\n* Tommy Blanchard http:\u002F\u002Ftommyblanchard.com\u002Fcategory\u002Fprojects [(RSS)](http:\u002F\u002Ftommyblanchard.com\u002Ffeeds\u002Fall.atom.xml)\n* Trevor Stephens http:\u002F\u002Ftrevorstephens.com\u002F [(RSS)](http:\u002F\u002Ftrevorstephens.com\u002Ffeed.xml)\n* Trey Causey http:\u002F\u002Ftreycausey.com\u002F [(RSS)](http:\u002F\u002Ftreycausey.com\u002Ffeeds\u002Fall.atom.xml)\n* UW 数据科学博客 http:\u002F\u002Fdatasciencedegree.wisconsin.edu\u002Fblog\u002F [(RSS)](http:\u002F\u002Fdatasciencedegree.wisconsin.edu\u002Ffeed\u002F)\n* Wellecks http:\u002F\u002Fwellecks.wordpress.com\u002F [(RSS)](http:\u002F\u002Fwellecks.wordpress.com\u002Ffeed\u002F)\n* Wes McKinney http:\u002F\u002Fwesmckinney.com\u002Farchives.html [(RSS)](http:\u002F\u002Fwesmckinney.com\u002Ffeeds\u002Fall.atom.xml)\n* 当我的MCMC轻轻采样时 http:\u002F\u002Ftwiecki.github.io\u002F [(RSS)](http:\u002F\u002Ftwiecki.github.io\u002Fatom.xml)\n* WildML http:\u002F\u002Fwww.wildml.com\u002F [(RSS)](http:\u002F\u002Fwww.wildml.com\u002Ffeed\u002F)\n* 会为了某些东西做些事情 http:\u002F\u002Frinzewind.org\u002Fblog-en [(RSS)](http:\u002F\u002Frinzewind.org\u002Ffeed-en)\n* Will wolf http:\u002F\u002Fwillwolf.io\u002F [(RSS)](http:\u002F\u002Fwillwolf.io\u002Ffeed\u002F)\n* WILL 的噪音 http:\u002F\u002Fwww.willmcginnis.com\u002F [(RSS)](http:\u002F\u002Fwww.willmcginnis.com\u002Ffeed\u002F)\n* William Lyon http:\u002F\u002Fwww.lyonwj.com\u002F [(RSS)](http:\u002F\u002Fwww.lyonwj.com\u002Fatom.xml)\n* Win-Vector 博客 http:\u002F\u002Fwww.win-vector.com\u002Fblog\u002F [(RSS)](http:\u002F\u002Fwww.win-vector.com\u002Fblog\u002Ffeed\u002F)\n* Yanir Seroussi http:\u002F\u002Fyanirseroussi.com\u002F [(RSS)](http:\u002F\u002Fyanirseroussi.com\u002Ffeed\u002F)\n* Zac Stewart http:\u002F\u002Fzacstewart.com\u002F [(RSS)](http:\u002F\u002Fzacstewart.com\u002Ffeed.xml)\n* ŷhat http:\u002F\u002Fblog.yhat.com\u002F [(RSS)](http:\u002F\u002Fblog.yhat.com\u002Frss.xml)\n* 量化之旅 http:\u002F\u002Foutlace.com\u002F [(RSS)](http:\u002F\u002Foutlace.com\u002Ffeed.xml)\n* 大トロ http:\u002F\u002Fblog.otoro.net\u002F [(RSS)](http:\u002F\u002Fblog.otoro.net\u002Ffeed.xml)\n\n## 致谢\n\n* 韦斯·麦金尼著《Python数据分析：使用Pandas、NumPy和IPython进行数据清洗》（http:\u002F\u002Fwww.amazon.com\u002FPython-Data-Analysis-Wrangling-IPython\u002Fdp\u002F1449319793）\n* 杰克·范德普拉斯编写的《2015年PyCon scikit-learn教程》（https:\u002F\u002Fgithub.com\u002Fjakevdp\u002Fsklearn_pycon2015）\n* 杰克·范德普拉斯编写的《Python数据科学手册》（https:\u002F\u002Fgithub.com\u002Fjakevdp\u002FPythonDataScienceHandbook）\n* 奥利维埃·格里塞尔编写的《使用scikit-learn和IPython实现并行机器学习》（https:\u002F\u002Fgithub.com\u002Fogrisel\u002Fparallel_ml_tutorial）\n* 艾伦·道尼编写的《利用Python计算方法进行统计推断》（https:\u002F\u002Fgithub.com\u002FAllenDowney\u002FCompStats）\n* 埃梅里克·达米安编写的《TensorFlow示例》（https:\u002F\u002Fgithub.com\u002Faymericdamien\u002FTensorFlow-Examples）\n* 帕拉格·K·米塔尔编写的《TensorFlow教程》（https:\u002F\u002Fgithub.com\u002Fpkmital\u002Ftensorflow_tutorials）\n* 纳森·林茨编写的《TensorFlow教程》（https:\u002F\u002Fgithub.com\u002Fnlintz\u002FTensorFlow-Tutorials）\n* 亚历山大·R·约翰森编写的《TensorFlow教程》（https:\u002F\u002Fgithub.com\u002Falrojo\u002Ftensorflow-tutorial）\n* 尼尚特·舒克拉编写的《TensorFlow书籍》（https:\u002F\u002Fgithub.com\u002FBinRoot\u002FTensorFlow-Book）\n* mila-udem组织的《2015年暑期学校》（https:\u002F\u002Fgithub.com\u002Fmila-udem\u002Fsummerschool2015）\n* 瓦莱里奥·马焦编写的《深度学习Keras与TensorFlow教程》（https:\u002F\u002Fgithub.com\u002Fleriomaggio\u002Fdeep-learning-keras-tensorflow）\n* Kaggle（https:\u002F\u002Fwww.kaggle.com\u002F）\n* Yhat博客（http:\u002F\u002Fblog.yhat.com\u002F）\n\n## 贡献\n\n欢迎贡献！如发现bug或有需求，请[提交issue](https:\u002F\u002Fgithub.com\u002Ftarrysingh\u002FMachine-Learning-Tutorials\u002F\u002Fissues)。\n\n## 联系方式\n\n如有任何问题、疑问或意见，欢迎随时联系我。\n\n* 邮箱：[tarry.singh@gmail.com](mailto:tarry.singh@gmail.com)\n* Twitter：[@tarrysingh](https:\u002F\u002Ftwitter.com\u002Ftarrysingh)\n* GitHub：[tarrysingh](https:\u002F\u002Fgithub.com\u002Ftarrysingh.com)\n* LinkedIn：[Tarry Singh](https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Ftarrysingh)\n* 官网：[tarrysingh.com](https:\u002F\u002Ftarrysingh.com)\n* Medium：[tarry@Medium](https:\u002F\u002Fmedium.com\u002F@tarrysingh)\n* Quora：[Tarry在Quora上的回答](https:\u002F\u002Fwww.quora.com\u002Fprofile\u002FTarry-Singh)\n\n## 许可证\n\n本仓库包含多种内容，其中一部分由Tarry Singh开发，另一部分来自第三方，大部分将由我维护。第三方内容根据其各自提供的许可证进行分发。\n\n最初由Donne Martin创建的内容于2017年以以下许可证发布。此后，我继续开发并维护该仓库，新增了PyTorch、Torch\u002FLua、MXNET等内容：\n\n* 我在此仓库中向您提供代码和资源，并采用开源许可证。\n\n    版权所有 © 2017 Tarry Singh\n\n    根据Apache许可证第2.0版（“许可证”）授权；除非遵守该许可证，否则不得使用本文件。您可以在以下网址获取许可证副本：\n\n       http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\n    除非适用法律另有规定或双方书面同意，否则软件按“原样”分发，不提供任何形式的保证或条件。有关特定语言的权限及限制，请参阅该许可证。","# Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 快速上手指南\n\n本仓库是一个汇集了机器学习（ML）、深度学习（DL）及人工智能（AI）优质教程的索引库，涵盖 PyTorch、TensorFlow、Theano、Pyro 等主流框架。所有教程均针对 **NVIDIA GPU** 进行了优化支持。\n\n## 环境准备\n\n在开始学习之前，请确保您的开发环境满足以下要求：\n\n*   **操作系统**: Linux (推荐 Ubuntu 20.04+), macOS, 或 Windows (需配置 WSL2)。\n*   **硬件要求**: \n    *   NVIDIA GPU (推荐 RTX 系列或更高)，已安装兼容的驱动程序。\n    *   至少 8GB 内存（处理大型数据集建议 16GB+）。\n*   **软件依赖**:\n    *   Python 3.8 - 3.10\n    *   Git\n    *   Jupyter Notebook \u002F JupyterLab\n    *   CUDA Toolkit & cuDNN (根据所选深度学习框架版本匹配)\n\n> **国内加速建议**: \n> *   推荐使用清华源或阿里源安装 Python 包，以加快下载速度。\n> *   若访问 GitHub 缓慢，可使用 `git clone` 镜像地址或通过代理加速。\n\n## 安装步骤\n\n### 1. 克隆仓库\n首先将教程仓库克隆到本地：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FTarrySingh\u002FArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials.git\ncd Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials\n```\n\n### 2. 创建虚拟环境并安装基础依赖\n建议使用 `conda` 或 `venv` 隔离环境。以下以 `pip` 配合国内镜像源为例：\n\n```bash\npython -m venv ai-tutorials-env\nsource ai-tutorials-env\u002Fbin\u002Factivate  # Windows 用户请使用: ai-tutorials-env\\Scripts\\activate\n\n# 使用清华源安装基础数据科学栈\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple numpy pandas matplotlib scikit-learn jupyterlab\n```\n\n### 3. 安装深度学习框架 (按需选择)\n根据您想学习的教程目录，安装对应的框架。**请确保您的 CUDA 版本与框架版本兼容**。\n\n*   **PyTorch (推荐)**:\n    ```bash\n    pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple torch torchvision torchaudio --index-url https:\u002F\u002Fdownload.pytorch.org\u002Fwhl\u002Fcu118\n    ```\n\n*   **TensorFlow**:\n    ```bash\n    pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple tensorflow\n    ```\n\n*   **其他框架 (Theano, Keras 等)**:\n    ```bash\n    pip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple theano keras\n    ```\n\n## 基本使用\n\n本仓库的核心内容是 `.ipynb` (Jupyter Notebook) 文件。以下是运行一个基础教程的步骤：\n\n### 1. 启动 Jupyter Lab\n在项目根目录下启动服务：\n\n```bash\njupyter lab\n```\n\n### 2. 选择教程笔记\n浏览器会自动打开界面，根据左侧目录结构选择您感兴趣的主题：\n\n*   **PyTorch 入门**: 进入 `pytorch\u002F` 目录，打开 `PyTorch NN Basics - Autograd Gradient Neural Network Loss Backprop.ipynb` 学习张量与自动求导基础。\n*   **TensorFlow 实战**: 进入 `deep-learning\u002Ftensor-flow-examples\u002Fnotebooks\u002F`，例如打开 `1_intro\u002Fbasic_operations.ipynb` 学习基本操作。\n*   **概率编程**: 进入 `deep-learning\u002FUBER-pyro\u002F` 参考 Pyro 示例。\n\n### 3. 运行示例代码\n打开任意 Notebook 后：\n1.  点击单元格（Cell）。\n2.  按 `Shift + Enter` 执行代码。\n3.  观察输出结果及可视化图表（如损失函数曲线、图像分类结果等）。\n\n> **提示**: 部分高级教程（如多 GPU 训练 `tsf-gpu.ipynb`）需要确保您的环境已正确识别到多个 GPU 设备。可通过运行 `import torch; print(torch.cuda.device_count())` 进行验证。","某医疗科技公司的算法团队正致力于开发基于深度学习的早期肺癌 CT 影像筛查系统，急需快速掌握从数据预处理到概率建模的全栈技术。\n\n### 没有 Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 时\n- **资源分散且筛选成本高**：工程师需在 GitHub、博客和技术论坛间反复跳转，难以区分过时的 Theano 教程与最新的 PyTorch 实战指南，浪费大量调研时间。\n- **行业落地参考缺失**：通用深度学习教程缺乏医疗、能源等垂直领域的具体案例，团队难以理解如何将抽象模型（如贝叶斯回归）映射到具体的病灶识别任务中。\n- **前沿技术跟进滞后**：对于 GPU 加速编程、可持续 AI 及 Web3 结合等 2023-2024 新兴话题，缺乏系统性的入门路径，导致技术选型保守，无法利用最新算力优化模型。\n\n### 使用 Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 后\n- **一站式权威索引**：直接通过目录定位到 Uber Pyro 的概率编程教程或 Netflix VectorFlow 实例，快速获取经过验证的代码片段，将环境搭建与基础学习周期缩短 50%。\n- **垂直场景精准对标**：参考列表中针对医药与健康行业的专项应用案例，团队迅速复现了适用于小样本医疗数据的半监督学习模型，显著提升了诊断准确率。\n- **技术栈实时同步**：依托每日更新的机制，工程师立即掌握了基于 NVIDIA GPU 的最新优化技巧及 Data Centric AI 理念，确保系统架构在未来三年内保持技术领先性。\n\nArtificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials 通过提供结构化、实时更新且涵盖多行业的教程索引，将研发团队从繁琐的信息检索中解放出来，使其能专注于核心算法的创新与落地。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FTarrySingh_Artificial-Intelligence-Deep-Learning-Machine-Learning-Tutorials_7bb5fcf4.png","TarrySingh","tarry.singh","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FTarrySingh_45fdf81d.jpg","€ntrepreneur, ℝesearcher, \"_developer_\" (systems guy - data, databases, infrastructure, cloud). Background in Nautical Engineering, astrʘn⊕my,⎩mατh⎭& ρhysicS","deepkapha.ai","Assen [NL] | Toronto [CA] | Middle East [UAE\u002FOM]","tarry.singh@deepkapha.com","tarrysingh","https:\u002F\u002Fdeepkapha.com","https:\u002F\u002Fgithub.com\u002FTarrySingh",[84,88,92,96,100,103,107,110,113,116],{"name":85,"color":86,"percentage":87},"Python","#3572A5",95.7,{"name":89,"color":90,"percentage":91},"HTML","#e34c26",2.6,{"name":93,"color":94,"percentage":95},"Java","#b07219",0.5,{"name":97,"color":98,"percentage":99},"C++","#f34b7d",0.3,{"name":101,"color":102,"percentage":99},"C#","#178600",{"name":104,"color":105,"percentage":106},"C","#555555",0.1,{"name":108,"color":109,"percentage":106},"Objective-C","#438eff",{"name":111,"color":112,"percentage":106},"Pascal","#E3F171",{"name":114,"color":115,"percentage":106},"MATLAB","#e16737",{"name":117,"color":118,"percentage":106},"GAP","#0000cc",3986,1642,"2026-04-18T06:05:59","NOASSERTION","未说明","需要 NVIDIA GPU（明确提及所有教程均由 NVIDIA GPU 支持和加速），具体型号、显存大小及 CUDA 版本未说明",{"notes":126,"python":123,"dependencies":127},"该仓库是一个教程合集，涵盖了多种深度学习框架（如 PyTorch, TensorFlow, Theano 等）和工具。README 明确指出所有教程均针对 NVIDIA GPU 进行了支持和加速。部分示例涉及 D 语言 (Dlang) 和 Lua。由于是教程集合，具体每个项目的依赖版本需参考其对应的子项目链接，此处仅列出主要涉及的库名称。",[128,129,130,131,132,133,134,135,136,137],"PyTorch","TensorFlow","Theano","Keras","Caffe","Pyro (Uber)","VectorFlow (Netflix)","scikit-learn","pandas","numpy",[16,139,14],"其他",[141,142,143,144,145,146,147,148,149,150,136,135,151,152,153,154,155,156,157,158],"machine-learning","deep-learning","tensorflow","python","pytorch","keras","lua","matplotlib","aws","kaggle","torch","artificial-intelligence","neural-network","convolutional-neural-networks","tensorflow-tutorials","python-data","ipython-notebook","capsule-network",null,"2026-03-27T02:49:30.150509","2026-04-19T09:14:23.357506",[],[]]