[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-Shujian2015--FreeML":3,"tool-Shujian2015--FreeML":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",145895,2,"2026-04-08T11:32:59",[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。",108111,"2026-04-08T11:23:26",[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},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],"插件",{"id":54,"name":55,"github_repo":56,"description_zh":57,"stars":58,"difficulty_score":10,"last_commit_at":59,"category_tags":60,"status":17},4487,"LLMs-from-scratch","rasbt\u002FLLMs-from-scratch","LLMs-from-scratch 是一个基于 PyTorch 的开源教育项目，旨在引导用户从零开始一步步构建一个类似 ChatGPT 的大型语言模型（LLM）。它不仅是同名技术著作的官方代码库，更提供了一套完整的实践方案，涵盖模型开发、预训练及微调的全过程。\n\n该项目主要解决了大模型领域“黑盒化”的学习痛点。许多开发者虽能调用现成模型，却难以深入理解其内部架构与训练机制。通过亲手编写每一行核心代码，用户能够透彻掌握 Transformer 架构、注意力机制等关键原理，从而真正理解大模型是如何“思考”的。此外，项目还包含了加载大型预训练权重进行微调的代码，帮助用户将理论知识延伸至实际应用。\n\nLLMs-from-scratch 特别适合希望深入底层原理的 AI 开发者、研究人员以及计算机专业的学生。对于不满足于仅使用 API，而是渴望探究模型构建细节的技术人员而言，这是极佳的学习资源。其独特的技术亮点在于“循序渐进”的教学设计：将复杂的系统工程拆解为清晰的步骤，配合详细的图表与示例，让构建一个虽小但功能完备的大模型变得触手可及。无论你是想夯实理论基础，还是为未来研发更大规模的模型做准备",90106,"2026-04-06T11:19:32",[35,15,13,14],{"id":62,"github_repo":63,"name":64,"description_en":65,"description_zh":66,"ai_summary_zh":66,"readme_en":67,"readme_zh":68,"quickstart_zh":69,"use_case_zh":70,"hero_image_url":71,"owner_login":72,"owner_name":73,"owner_avatar_url":74,"owner_bio":75,"owner_company":76,"owner_location":77,"owner_email":73,"owner_twitter":73,"owner_website":78,"owner_url":79,"languages":73,"stars":80,"forks":81,"last_commit_at":82,"license":73,"difficulty_score":83,"env_os":84,"env_gpu":85,"env_ram":85,"env_deps":86,"category_tags":89,"github_topics":91,"view_count":32,"oss_zip_url":73,"oss_zip_packed_at":73,"status":17,"created_at":96,"updated_at":97,"faqs":98,"releases":99},5559,"Shujian2015\u002FFreeML","FreeML","A List of Data Science\u002FMachine Learning Resources (Mostly Free)","FreeML 是一份精心整理的数据科学与机器学习资源清单，旨在为学习者提供一条从入门到进阶的清晰路径。面对海量且分散的学习资料，初学者往往难以抉择，FreeML 通过筛选绝大多数免费的高质量课程、经典教材和视频讲座，有效解决了“学什么”和“怎么学”的难题。\n\n这份资源特别适合非计算机专业但渴望踏入数据科学领域的爱好者，同时也适用于希望系统巩固基础的开发者或研究人员。其独特亮点在于作者结合自身两年的学习经验与年度规划，在理论深度与实践可行性之间取得了良好平衡。清单不仅涵盖了机器学习、自然语言处理、深度学习等核心领域，还贴心地提供了\"30 天速成计划”，帮助用户快速建立知识框架。从吴恩达的经典课程到斯坦福的统计学习讲义，再到 Keras 快速上手指南，FreeML 将零散的资源串联成体系，是开启数据科学之旅的实用向导。","# Data Science Resources (Mostly Free)\n\nThe first half is more or less my learning path in the past two years while the second half is my plan for this year. I tried to make a balance between comprehension and doability. For more extensive lists, you can check [Github search](https:\u002F\u002Fgithub.com\u002Fsearch?utf8=%E2%9C%93&q=awesome+machine+learning&type=) or [CS video lectures](https:\u002F\u002Fgithub.com\u002FDeveloper-Y\u002Fcs-video-courses)\n\nHope the list is helpful, especially to whom are not in CS major but interested in data science!\n\n***\n## Table of Contents\n\n* [One Month Plan](#one-month-plan)\n* [Machine Learning](#machine-learning)\n* [Natural Language Processing](#natural-language-processing)\n* [Deep Learning](#deep-learning)\n* [Systems](#systems)\n* [Analytics](#analytics)\n* [Reinforcement Learning](#reinforcement-learning)\n* [Other Courses](#others)\n* [Interviews](#interviews)\n* [Bayesian](#bayesian)\n* [Time series](#time-series)\n* [Quant](#quant)\n* [More Lists](#more)\n\n***\n## One Month Plan:\n\nYou may find the list overwhelming. Here is my suggestion if you want to have some basic understanding in one month:\n  * Learn Python the hard way: [Free book](https:\u002F\u002Flearnpythonthehardway.org\u002Fbook\u002F)\n  * Stanford Statistical Learning ([Course page](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout)) or Coursera Stanford by Andrew Ng ([Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning), [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN))\n  * Ng’s deep learning courses: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning)  \n  * Keras in 30 sec: [Link](https:\u002F\u002Fkeras.io\u002F#getting-started-30-seconds-to-keras)\n  * Database by Stanford: [Course](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fdatabases-self-paced)\n\n## Machine Learning:\n\n### - Videos:\n  * Stanford Statistical Learning: [Course page](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout)\n  * Coursera Stanford by Andrew Ng: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning), [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN)\n  * Stanford 229: [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UzxYlbK2c7E&list=PLA89DCFA6ADACE599), [Course page](\nhttp:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus.html)    \n  * Machine Learning Foundations (機器學習基石): [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fntumlone-mathematicalfoundations)\n, [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLXVfgk9fNX2I7tB6oIINGBmW50rrmFTqf&disable_polymer=true)\n  * Machine Learning Techniques (機器學習技法): [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLXVfgk9fNX2IQOYPmqjqWsNUFl2kpk1U2&disable_polymer=true)\n  * CMU 701 by Tom Mitchell: [Course page](http:\u002F\u002Fwww.cs.cmu.edu\u002F~tom\u002F10701_sp11\u002Flectures.shtml)\n\n### - Textbooks:\n  * Introduction to Statistical Learning: [pdf](http:\u002F\u002Fwww-bcf.usc.edu\u002F~gareth\u002FISL\u002FISLR%20First%20Printing.pdf)\n  * Computer Age Statistical Inference: Algorithms, Evidence, and Data Science: [pdf](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FCASI_files\u002FPDF\u002Fcasi.pdf)  \n  * The Elements of Statistical Learning: [pdf](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FPapers\u002FESLII.pdf)\n  * Machine Learning Yearning: [Website](http:\u002F\u002Fwww.mlyearning.org\u002F)\n\n### - Comments:\nStatistical Learning is the introduction course. It is free to earn a certificate. It follows Introduction to Statistical Learning book closely. Coursera Stanford by Andrew Ng is another introduction course course and quite popular. Taking either of them is enough for most of data science positions. People want to go deeper can take 229 or 701 and read ESL book.\n\n***\n\n\n## Natural Language Processing: \n### - Videos:\n  * Stanford - Basic NLP course on Coursera: [Videos](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOFZnDyrlW3-nI7tMLtmiJZ&disable_polymer=true), [Slides](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002FNLPCourseraSlides.html)\n  * Stanford - CS224n Natural Language Processing with Deep Learning: [Course web](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F), [Videos](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6) (2019 winter version: [videos](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z))\n  * CMU - Neural Nets for NLP 2017: [Course web](http:\u002F\u002Fwww.phontron.com\u002Fclass\u002Fnn4nlp2017\u002Fschedule.html), [Videos](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8ABXzdqtOpB_eqBlVAz_xPT)\n  * University of Oxford and DeepMind - Deep Learning for Natural Language Processing: 2016-2017: [Course web](http:\u002F\u002Fwww.cs.ox.ac.uk\u002Fteaching\u002Fcourses\u002F2016-2017\u002Fdl\u002F), [Videos and slides](https:\u002F\u002Fgithub.com\u002Foxford-cs-deepnlp-2017\u002Flectures)\n  * Sequence Models by Andrew Ng on Coursera: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fnlp-sequence-models)\n\n### - Books:\n  * Speech and Language Processing (3rd ed. draft): [Book](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F)\n  * An Introduction to Information Retrieval: [pdf](https:\u002F\u002Fnlp.stanford.edu\u002FIR-book\u002Fpdf\u002Firbookonlinereading.pdf)\n  * Deep Learning (Some chapters or sections): [Book](http:\u002F\u002Fwww.deeplearningbook.org)\n  * A Primer on Neural Network Models for Natural Language Processing: [Paper](http:\u002F\u002Fu.cs.biu.ac.il\u002F~yogo\u002Fnnlp.pdf). Goldberg also published a new book this year\n  * NLP by Jacob Eisenstein: [pdf](https:\u002F\u002Fgithub.com\u002Fjacobeisenstein\u002Fgt-nlp-class\u002Ftree\u002Fmaster\u002Fnotes). Free book draft\n  * Deep Learning in Natural Language Processing by Deng, Li: [Amazon](https:\u002F\u002Fwww.springer.com\u002Fus\u002Fbook\u002F9789811052088)\n\n\n### - Packages:\n  * NLTK: http:\u002F\u002Fwww.nltk.org\u002F\n  * Standord packages: https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002F\n\n### - Comments:\nThe basic NLP course by Stanford is the fundamental one. SLP 3ed follows this course. After this, feel free to take one of the three NLP+DL courses. They basically cover same topics. The Stanford one have HWs available online. CMU one follows Goldberg's book. Deepmind one is much shorter.\n\n### - More:\nSome other people's collections: [NLP](https:\u002F\u002Fgithub.com\u002Fkeon\u002Fawesome-nlp), [DL-NLP](https:\u002F\u002Fgithub.com\u002Fbrianspiering\u002Fawesome-dl4nlp), [Speech and NLP](https:\u002F\u002Fgithub.com\u002Fedobashira\u002Fspeech-language-processing), [Speech](https:\u002F\u002Fgithub.com\u002Fzzw922cn\u002Fawesome-speech-recognition-speech-synthesis-papers), [RNN](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-rnn)\n\n***\n\n## Deep Learning\n\n### - Videos:\n  * Ng’s deep learning courses: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning). This specialization is so popular. Prof. Ng covers all a lot of details and he is really a good teacher.\n  * Tensorflow. Stanford CS20SI: [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQ0sVbIj3URf94DQtGPJV629ctn2c1zN-)\n  * Stanford 231n: Convolutional Neural Networks for Visual Recognition (Spring 2017): [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv), [Couse page](http:\u002F\u002Fcs231n.stanford.edu\u002F)\n  * Stanford 224n: Natural Language Processing with Deep Learning (Winter 2017): [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6), [Course page](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F)\n  * The self-driving car is a really hot topic recently. Take a look at this short course to see how it works. MIT 6.S094: Deep Learning for Self-Driving Cars: [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf), [Couse page](http:\u002F\u002Fselfdrivingcars.mit.edu\u002F)\n  * Neural Networks for Machine Learning by Hinton: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks). This course is so hard for me but it covers almost everything about neural networks. Prof. Hinton is the hero.\n  * FAST.ai: [Course](http:\u002F\u002Fwww.fast.ai\u002F)\n\n### - Books:\n  * Deep learning book by Ian Goodfellow: http:\u002F\u002Fwww.deeplearningbook.org\u002F. Very detailed reference book. \n  * ArXiv for research updates: https:\u002F\u002Farxiv.org\u002F. I found it the mobile version of Feedly is useful to follow ArXiv. Also, try https:\u002F\u002Fdeeplearn.org\u002F or http:\u002F\u002Fwww.arxiv-sanity.com\u002Ftop.\n\n### - Other: \n  * LSTM: [My collection](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fml-4-shujian-liu\u002F)\n\n### - Comments:\nNg's courses are already good enough. Reading Part 2 of Goodfellow's book can also be helpful. Learning one kind of DL packages is important, such as Keras, TF or Pytorch. People may choose a focus, either CV or NLP. People want to have deeper understanding of DL can take Hinton's course and read Part 3 of Goodfellow's book. Fast.ai has very practical courses.\n\n\n***  \n  \n  \n  \n  \n## Systems:\n  * Docker Mastery: [Udemy](https:\u002F\u002Fwww.udemy.com\u002Fdocker-mastery\u002Flearn\u002Fv4\u002Foverview)\n  * The Ultimate Hands-On Hadoop: [Udemy](https:\u002F\u002Fwww.udemy.com\u002Fthe-ultimate-hands-on-hadoop-tame-your-big-data\u002Flearn\u002Fv4\u002Foverview)  \n  * Spark and Python for Big Data with PySpark: [Udemy](https:\u002F\u002Fwww.udemy.com\u002Fspark-and-python-for-big-data-with-pyspark\u002Flearn\u002Fv4)\n  \n  \n  \n  \n***\n  \n## Analytics:\n  * Lean Analytics: [Amazon](https:\u002F\u002Fwww.amazon.com\u002FLean-Analytics-Better-Startup-Faster\u002Fdp\u002FB00AG66LTM\u002F)\n  * Data Science for Business: [Amazon](https:\u002F\u002Fwww.amazon.com\u002FData-Science-Business-Data-Analytic-Thinking\u002Fdp\u002F1449361323\u002F)\n  * Data Smart: [Amazon](https:\u002F\u002Fwww.amazon.com\u002FData-Smart-Science-Transform-Information\u002Fdp\u002F111866146X\u002F)\n  * Storytelling with Data: [Amazon](https:\u002F\u002Fwww.amazon.com\u002FStorytelling-Data-Visualization-Business-Professionals\u002Fdp\u002F1119002257)\n\n\n\n\n***\n\n\n\n\n## Reinforcement Learning:\n### - Videos:\n  * Udacity: [Course](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Freinforcement-learning--ud600) \n  * UCL Course on RL by David Silver: [Course page](http:\u002F\u002Fwww0.cs.ucl.ac.uk\u002Fstaff\u002Fd.silver\u002Fweb\u002FTeaching.html)\n  * CS 294: Deep Reinforcement Learning by UC Berkeley, Fall 2017: [Course page](http:\u002F\u002Frll.berkeley.edu\u002Fdeeprlcourse\u002F) \n### - Books:\n  * Reinforcement Learning: An Introduction (2nd): [pdf](http:\u002F\u002Fincompleteideas.net\u002Fbook\u002Fthe-book-2nd.html)\n\n\n\n  \n  \n***  \n  \n  \n  \n  \n## Others:\n  * Recommender System by UMN: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Frecommender-systems) \n  * Mining Massive Datasets by Stanford: [Free book](http:\u002F\u002Fwww.mmds.org\u002F), [Course](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fmining-massive-datasets-self-paced)\n  * Introduction to Algorithms by MIT: [Course page with videos](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-006-introduction-to-algorithms-fall-2011\u002F)\n  * Database by Stanford: [Course](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fdatabases-self-paced)\n  * How to Win a Data Science Competition: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fcompetitive-data-science)\n  * How to finish a Data Challenge: [Kaggle EDA kernels](https:\u002F\u002Fwww.kaggle.com\u002Fkernels?sortBy=votes&group=everyone&pageSize=20)\n  \n  \n*** \n  \n  \n## Interviews:\n\n\n### - Lists with Solutions:\n  * 111 Data Science Interview Questions & Detailed Answers: [Link](https:\u002F\u002Frpubs.com\u002FJDAHAN\u002F172473?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 40 Interview Questions asked at Startups in Machine Learning \u002F Data Science [Link](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2016\u002F09\u002F40-interview-questions-asked-at-startups-in-machine-learning-data-science\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 100 Data Science Interview Questions and Answers (General) for 2017 [Link](https:\u002F\u002Fwww.dezyre.com\u002Farticle\u002F100-data-science-interview-questions-and-answers-general-for-2017\u002F184?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 21 Must-Know Data Science Interview Questions and Answers [Link](http:\u002F\u002Fwww.kdnuggets.com\u002F2016\u002F02\u002F21-data-science-interview-questions-answers.html?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 45 Questions to test a data scientist on basics of Deep Learning (along with solution) [Link](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2017\u002F01\u002Fmust-know-questions-deep-learning\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 30 Questions to test a data scientist on Natural Language Processing [Link](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2017\u002F07\u002F30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * Questions on Stackoverflow: [Link](https:\u002F\u002Fstackoverflow.com\u002Fquestions\u002Ftagged\u002Fmachine-learning?sort=votes&pageSize=15)\n  * Compare two models: [My collection](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fml-2-shujian-liu\u002F)\n  \n### - Without Solutions:\n  * Over 100 Data Science Interview Questions [Link](http:\u002F\u002Fwww.learndatasci.com\u002Fdata-science-interview-questions\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 20 questions to detect fake data scientists [Link](https:\u002F\u002Fwww.import.io\u002Fpost\u002F20-questions-to-detect-fake-data-scientists\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * Question on Glassdoor: [link](https:\u002F\u002Fwww.glassdoor.com\u002FInterview\u002Fdata-scientist-interview-questions-SRCH_KO0,14.htm)\n  \n\n\n\n\n***\n\n# Topics to Learn ->\n\n*** \n\n## Bayesian:\n### - Courses:\n  * Bayesian Statistics: From Concept to Data Analysis: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fbayesian-statistics)\n  * Bayesian Methods for Machine Learning: [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fbayesian-methods-in-machine-learning)\n  * Statistical Rethinking: [Course Page](http:\u002F\u002Fxcelab.net\u002Frm\u002Fstatistical-rethinking\u002F) (Recorded Lectures: Winter 2015, Fall 2017)\n\n### - Book:\n  * Bayesian Data Analysis, Third Edition\n  * Applied Predictive Modeling\n\n\n\n*** \n\n\n\n## Time series:\n### - Courses:\n  * Time Series Forecasting (Udacity): [Udacity](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Ftime-series-forecasting--ud980)\n  * Topics in Mathematics with Applications in Finance (MIT): [Course page](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-s096-topics-in-mathematics-with-applications-in-finance-fall-2013\u002F), [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63ctJIEC1UnZ0btsphnnoHR)\n\n### - Books:\n  * Time Series Analysis and Its Applications: [Springer](http:\u002F\u002Fwww.springer.com\u002Fus\u002Fbook\u002F9783319524511)\n\n### - With LSTM:\n  * https:\u002F\u002Fmachinelearningmastery.com\u002Ftime-series-prediction-lstm-recurrent-neural-networks-python-keras\u002F\n  * https:\u002F\u002Fmachinelearningmastery.com\u002Fmultivariate-time-series-forecasting-lstms-keras\u002F\n  * More: https:\u002F\u002Fmachinelearningmastery.com\u002F?s=Time+Series&submit=Search\n\n\n\n*** \n\n\n\n## Quant:\n### - Books:\n  * Heard on the Street: Quantitative Questions from Wall Street Job Interviews by Timothy Falcon Crack: [Amazon]( https:\u002F\u002Fwww.amazon.com\u002FHeard-Street-Quantitative-Questions-Interviews\u002Fdp\u002F0994138636\u002F)\n  * A Practical Guide To Quantitative Finance Interviews by Xinfeng Zhou: [Amazon](https:\u002F\u002Fwww.amazon.com\u002FPractical-Guide-Quantitative-Finance-Interviews\u002Fdp\u002F1438236662\u002F)\n\n### - Courses:\n  * Financial Markets with Robert Shiller (Yale): [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8FB14A2200B87185), [Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Ffinancial-markets-global)\n  * Topics in Mathematics with Applications in Finance (MIT): [Youtube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63ctJIEC1UnZ0btsphnnoHR), [Course page](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-s096-topics-in-mathematics-with-applications-in-finance-fall-2013\u002F)\n\n### - Other:\n  * A Collection of Dice Problems: [pdf](http:\u002F\u002Fwww.madandmoonly.com\u002Fdoctormatt\u002Fmathematics\u002Fdice1.pdf)\n\n\n\n***\n\n\n## More:\n  * Computer Science courses with video lectures: https:\u002F\u002Fgithub.com\u002FDeveloper-Y\u002Fcs-video-courses\n  * The Open Source Data Science Masters: http:\u002F\u002Fdatasciencemasters.org\n","# 数据科学资源（大部分免费）\n\n前半部分大致是我过去两年的学习路径，后半部分则是我今年的计划。我在理解和可操作性之间尽量做到了平衡。如果需要更全面的列表，可以查看 [Github 搜索](https:\u002F\u002Fgithub.com\u002Fsearch?utf8=%E2%9C%93&q=awesome+machine+learning&type=) 或 [CS 视频课程](https:\u002F\u002Fgithub.com\u002FDeveloper-Y\u002Fcs-video-courses)\n\n希望这份清单对大家有所帮助，尤其是那些非计算机专业但对数据科学感兴趣的朋友！\n\n***\n## 目录\n\n* [一个月计划](#one-month-plan)\n* [机器学习](#machine-learning)\n* [自然语言处理](#natural-language-processing)\n* [深度学习](#deep-learning)\n* [系统](#systems)\n* [分析](#analytics)\n* [强化学习](#reinforcement-learning)\n* [其他课程](#others)\n* [面试](#interviews)\n* [贝叶斯](#bayesian)\n* [时间序列](#time-series)\n* [量化](#quant)\n* [更多列表](#more)\n\n***\n## 一个月计划：\n\n你可能会觉得这个列表有些庞大。如果你希望在一个月内获得一些基础知识，我的建议如下：\n  * 《笨办法学 Python》：[免费书籍](https:\u002F\u002Flearnpythonthehardway.org\u002Fbook\u002F)\n  * 斯坦福统计学习课程（[课程页面](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout)）或吴恩达的 Coursera 斯坦福课程（[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)，[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN)）\n  * 吴恩达的深度学习课程：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning)  \n  * 30 秒学会 Keras：[链接](https:\u002F\u002Fkeras.io\u002F#getting-started-30-seconds-to-keras)\n  * 斯坦福数据库课程：[课程](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fdatabases-self-paced)\n\n## 机器学习：\n\n### - 视频：\n  * 斯坦福统计学习课程：[课程页面](https:\u002F\u002Flagunita.stanford.edu\u002Fcourses\u002FHumanitiesSciences\u002FStatLearning\u002FWinter2016\u002Fabout)\n  * 吴恩达的 Coursera 斯坦福课程：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning)，[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=PPLop4L2eGk&list=PLLssT5z_DsK-h9vYZkQkYNWcItqhlRJLN)\n  * 斯坦福 CS229：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=UzxYlbK2c7E&list=PLA89DCFA6ADACE599)，[课程页面](\nhttp:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus.html)    \n  * 机器学习基石：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fntumlone-mathematicalfoundations)\n, [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLXVfgk9fNX2I7tB6oIINGBmW50rrmFTqf&disable_polymer=true)\n  * 机器学习技法：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLXVfgk9fNX2IQOYPmqjqWsNUFl2kpk1U2&disable_polymer=true)\n  * 卡内基梅隆大学汤姆·米切尔的 CMU 701：[课程页面](http:\u002F\u002Fwww.cs.cmu.edu\u002F~tom\u002F10701_sp11\u002Flectures.shtml)\n\n### - 教材：\n  * 统计学习导论：[PDF](http:\u002F\u002Fwww-bcf.usc.edu\u002F~gareth\u002FISL\u002FISLR%20First%20Printing.pdf)\n  * 计算机时代的统计推断：算法、证据与数据科学：[PDF](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FCASI_files\u002FPDF\u002Fcasi.pdf)  \n  * 统计学习要素：[PDF](https:\u002F\u002Fweb.stanford.edu\u002F~hastie\u002FPapers\u002FESLII.pdf)\n  * 机器学习渴望：[网站](http:\u002F\u002Fwww.mlyearning.org\u002F)\n\n### - 评论：\n统计学习是入门课程，可以免费获得证书。它与《统计学习导论》一书内容高度一致。吴恩达的 Coursera 斯坦福课程也是另一门非常受欢迎的入门课程。对于大多数数据科学岗位来说，选修其中一门就足够了。如果想深入学习，可以选择 CS229 或 CMU 701，并阅读 ESL 书籍。\n\n***\n\n\n## 自然语言处理： \n### - 视频：\n  * 斯坦福基础 NLP 课程（Coursera）：[视频](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOFZnDyrlW3-nI7tMLtmiJZ&disable_polymer=true)，[幻灯片](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002FNLPCourseraSlides.html)\n  * 斯坦福 CS224n 自然语言处理与深度学习：[课程官网](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F)，[视频](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8ABXzdqtOpB_eqBlVAz_xPT)（2019 年冬季版：[视频](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z)）\n  * 卡内基梅隆大学 2017 年神经网络用于 NLP：[课程官网](http:\u002F\u002Fwww.phontron.com\u002Fclass\u002Fnn4nlp2017\u002Fschedule.html)，[视频](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8ABXzdqtOpB_eqBlVAz_xPT)\n  * 牛津大学和 DeepMind 的深度学习用于自然语言处理：2016–2017 年：[课程官网](http:\u002F\u002Fwww.cs.ox.ac.uk\u002Fteaching\u002Fcourses\u002F2016-2017\u002Fdl\u002F)，[视频和幻灯片](https:\u002F\u002Fgithub.com\u002Foxford-cs-deepnlp-2017\u002Flectures)\n  * 吴恩达的 Coursera 序列模型课程：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fnlp-sequence-models)\n\n### - 书籍：\n  * 语音与语言处理（第 3 版草稿）：[书籍](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F)\n  * 信息检索导论：[PDF](https:\u002F\u002Fnlp.stanford.edu\u002FIR-book\u002Fpdf\u002Firbookonlinereading.pdf)\n  * 深度学习（部分章节或小节）：[书籍](http:\u002F\u002Fwww.deeplearningbook.org)\n  * 自然语言处理神经网络模型入门：[论文](http:\u002F\u002Fu.cs.biu.ac.il\u002F~yogo\u002Fnnlp.pdf)。戈德堡今年也出版了一本新书\n  * 雅各布·艾森斯坦的 NLP：[PDF](https:\u002F\u002Fgithub.com\u002Fjacobeisenstein\u002Fgt-nlp-class\u002Ftree\u002Fmaster\u002Fnotes)。免费书籍草稿\n  * 邓、李合著的《自然语言处理中的深度学习》：[亚马逊](https:\u002F\u002Fwww.springer.com\u002Fus\u002Fbook\u002F9789811052088)\n\n\n### - 工具包：\n  * NLTK：http:\u002F\u002Fwww.nltk.org\u002F\n  * 斯坦福工具包：https:\u002F\u002Fnlp.stanford.edu\u002Fsoftware\u002F\n\n### - 评论：\n斯坦福的基础 NLP 课程是最为根本的。SLP 第 3 版正是基于这门课程编写的。在此之后，你可以选择三门 NLP+DL 课程中的一门。它们的内容基本相同。斯坦福的课程有在线作业可供练习。卡内基梅隆大学的课程则以戈德堡的书为基础。而 Deepmind 的课程则要短得多。\n\n### - 更多：\n其他人整理的一些列表：[NLP](https:\u002F\u002Fgithub.com\u002Fkeon\u002Fawesome-nlp)，[DL-NLP](https:\u002F\u002Fgithub.com\u002Fbrianspiering\u002Fawesome-dl4nlp)，[语音与 NLP](https:\u002F\u002Fgithub.com\u002Fedobashira\u002Fspeech-language-processing)，[语音](https:\u002F\u002Fgithub.com\u002Fzzw922cn\u002Fawesome-speech-recognition-speech-synthesis-papers)，[RNN](https:\u002F\u002Fgithub.com\u002Fkjw0612\u002Fawesome-rnn)\n\n***\n\n## 深度学习\n\n### - 视频：\n  * 吴恩达的深度学习课程：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fdeep-learning)。这个专项课程非常受欢迎。吴教授讲解得非常细致，是一位非常优秀的老师。\n  * TensorFlow. 斯坦福CS20SI：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLQ0sVbIj3URf94DQtGPJV629ctn2c1zN-)\n  * 斯坦福231n：用于视觉识别的卷积神经网络（2017年春季）：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6), [课程页面](http:\u002F\u002Fcs231n.stanford.edu\u002F)\n  * 斯坦福224n：深度学习自然语言处理（2017年冬季）：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL3FW7Lu3i5Jsnh1rnUwq_TcylNr7EkRe6), [课程页面](http:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224n\u002F)\n  * 自动驾驶汽车是最近非常热门的话题。可以看看这门简短的课程，了解其工作原理。MIT 6.S094：自动驾驶汽车的深度学习：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLrAXtmErZgOeiKm4sgNOknGvNjby9efdf), [课程页面](http:\u002F\u002Fselfdrivingcars.mit.edu\u002F)\n  * 辛顿的机器学习神经网络课程：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks)。这门课程对我来说非常难，但它几乎涵盖了神经网络的所有内容。辛顿教授堪称英雄。\n  * FAST.ai：[课程](http:\u002F\u002Fwww.fast.ai\u002F)\n\n### - 书籍：\n  * 伊恩·古德费洛的深度学习书：http:\u002F\u002Fwww.deeplearningbook.org\u002F。一本非常详尽的参考书。\n  * ArXiv用于研究更新：https:\u002F\u002Farxiv.org\u002F。我发现使用ArXiv的移动版Feedly来关注很有用。此外，也可以尝试https:\u002F\u002Fdeeplearn.org\u002F或http:\u002F\u002Fwww.arxiv-sanity.com\u002Ftop。\n\n### - 其他：\n  * LSTM：[我的收藏](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fml-4-shujian-liu\u002F)\n\n### - 评论：\n吴教授的课程已经足够好了。阅读古德费洛的第二部分也会很有帮助。学习一种深度学习框架很重要，比如Keras、TensorFlow或PyTorch。人们可以选择一个方向，要么是计算机视觉，要么是自然语言处理。如果想对深度学习有更深入的理解，可以选修辛顿的课程并阅读古德费洛的第三部分。Fast.ai的课程非常实用。\n\n\n***  \n  \n  \n  \n  \n## 系统：\n  * Docker精通：[Udemy](https:\u002F\u002Fwww.udemy.com\u002Fdocker-mastery\u002Flearn\u002Fv4\u002Foverview)\n  * 终极动手Hadoop：[Udemy](https:\u002F\u002Fwww.udemy.com\u002Fthe-ultimate-hands-on-hadoop-tame-your-big-data\u002Flearn\u002Fv4\u002Foverview)  \n  * 使用PySpark进行大数据分析的Spark和Python：[Udemy](https:\u002F\u002Fwww.udemy.com\u002Fspark-and-python-for-big-data-with-pyspark\u002Flearn\u002Fv4)\n  \n  \n  \n  \n***\n  \n## 分析：\n  * 精益数据分析：[亚马逊](https:\u002F\u002Fwww.amazon.com\u002FLean-Analytics-Better-Startup-Faster\u002Fdp\u002FB00AG66LTM\u002F)\n  * 商业中的数据科学：[亚马逊](https:\u002F\u002Fwww.amazon.com\u002FData-Science-Business-Data-Analytic-Thinking\u002Fdp\u002F1449361323\u002F)\n  * 数据智能：[亚马逊](https:\u002F\u002Fwww.amazon.com\u002FData-Smart-Science-Transform-Information\u002Fdp\u002F111866146X\u002F)\n  * 数据可视化讲故事：[亚马逊](https:\u002F\u002Fwww.amazon.com\u002FStorytelling-Data-Visualization-Business-Professionals\u002Fdp\u002F1119002257)\n\n\n\n\n***\n\n\n\n\n## 强化学习：\n### - 视频：\n  * Udacity：[课程](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Freinforcement-learning--ud600) \n  * UCL戴维·西尔弗的强化学习课程：[课程页面](http:\u002F\u002Fwww0.cs.ucl.ac.uk\u002Fstaff\u002Fd.silver\u002Fweb\u002FTeaching.html)\n  * UC伯克利CS 294：深度强化学习，2017年秋季：[课程页面](http:\u002F\u002Frll.berkeley.edu\u002Fdeeprlcourse\u002F) \n### - 书籍：\n  * 强化学习：导论（第2版）：[pdf](http:\u002F\u002Fincompleteideas.net\u002Fbook\u002Fthe-book-2nd.html)\n\n\n\n  \n  \n***  \n  \n  \n  \n  \n## 其他：\n  * 明尼苏达大学的推荐系统：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Frecommender-systems) \n  * 斯坦福的大规模数据挖掘：[免费书籍](http:\u002F\u002Fwww.mmds.org\u002F)，[课程](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fmining-massive-datasets-self-paced)\n  * MIT的算法导论：[带有视频的课程页面](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-006-introduction-to-algorithms-fall-2011\u002F)\n  * 斯坦福的数据库：[课程](http:\u002F\u002Fonline.stanford.edu\u002Fcourse\u002Fdatabases-self-paced)\n  * 如何赢得数据科学竞赛：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fcompetitive-data-science)\n  * 如何完成数据挑战：[Kaggle EDA内核](https:\u002F\u002Fwww.kaggle.com\u002Fkernels?sortBy=votes&group=everyone&pageSize=20)\n  \n  \n*** \n  \n  \n## 面试：\n\n\n### - 带答案的列表：\n  * 111道数据科学面试题及详细解答：[链接](https:\u002F\u002Frpubs.com\u002FJDAHAN\u002F172473?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 机器学习\u002F数据科学初创公司常问的40道面试题 [链接](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2016\u002F09\u002F40-interview-questions-asked-at-startups-in-machine-learning-data-science\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 2017年通用的数据科学面试题及答案100道 [链接](https:\u002F\u002Fwww.dezyre.com\u002Farticle\u002F100-data-science-interview-questions-and-answers-general-for-2017\u002F184?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 必须掌握的21道数据科学面试题及答案 [链接](http:\u002F\u002Fwww.kdnuggets.com\u002F2016\u002F02\u002F21-data-science-interview-questions-answers.html?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 测试数据科学家深度学习基础的45道题目（附解答） [链接](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2017\u002F01\u002Fmust-know-questions-deep-learning\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 测试数据科学家自然语言处理能力的30道题目 [链接](https:\u002F\u002Fwww.analyticsvidhya.com\u002Fblog\u002F2017\u002F07\u002F30-questions-test-data-scientist-natural-language-processing-solution-skilltest-nlp\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * Stackoverflow上的问题：[链接](https:\u002F\u002Fstackoverflow.com\u002Fquestions\u002Ftagged\u002Fmachine-learning?sort=votes&pageSize=15)\n  * 比较两个模型：[我的收藏](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fml-2-shujian-liu\u002F)\n  \n### - 不带答案的：\n  * 超过100道数据科学面试题 [链接](http:\u002F\u002Fwww.learndatasci.com\u002Fdata-science-interview-questions\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * 20道检测假数据科学家的问题 [链接](https:\u002F\u002Fwww.import.io\u002Fpost\u002F20-questions-to-detect-fake-data-scientists\u002F?lipi=urn%3Ali%3Apage%3Ad_flagship3_pulse_read%3BgFdjeopHQ5C1%2BT367egIug%3D%3D)\n  * Glassdoor上的问题：[链接](https:\u002F\u002Fwww.glassdoor.com\u002FInterview\u002Fdata-scientist-interview-questions-SRCH_KO0,14.htm)\n  \n\n\n\n\n***\n\n# 学习主题 ->\n\n*** \n\n## 贝叶斯：\n\n### - 课程：\n  * 贝叶斯统计：从概念到数据分析：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fbayesian-statistics)\n  * 机器学习中的贝叶斯方法：[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fbayesian-methods-in-machine-learning)\n  * 统计再思考：[课程页面](http:\u002F\u002Fxcelab.net\u002Frm\u002Fstatistical-rethinking\u002F)（2015年冬季、2017年秋季录制的讲座）\n\n### - 书籍：\n  * 贝叶斯数据分析（第三版）\n  * 应用预测建模\n\n\n\n*** \n\n\n\n## 时间序列：\n### - 课程：\n  * 时间序列预测（Udacity）：[Udacity](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Ftime-series-forecasting--ud980)\n  * 数学专题及其在金融中的应用（MIT）：[课程页面](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-s096-topics-in-mathematics-with-applications-in-finance-fall-2013\u002F)，[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63ctJIEC1UnZ0btsphnnoHR)\n\n### - 书籍：\n  * 时间序列分析及其应用：[Springer](http:\u002F\u002Fwww.springer.com\u002Fus\u002Fbook\u002F9783319524511)\n\n### - 使用LSTM：\n  * https:\u002F\u002Fmachinelearningmastery.com\u002Ftime-series-prediction-lstm-recurrent-neural-networks-python-keras\u002F\n  * https:\u002F\u002Fmachinelearningmastery.com\u002Fmultivariate-time-series-forecasting-lstms-keras\u002F\n  * 更多：https:\u002F\u002Fmachinelearningmastery.com\u002F?s=Time+Series&submit=Search\n\n\n\n*** \n\n\n\n## 量化：\n### - 书籍：\n  * 街头传闻：华尔街求职面试中的量化问题，作者：蒂莫西·法尔孔·克拉克：[Amazon]( https:\u002F\u002Fwww.amazon.com\u002FHeard-Street-Quantitative-Questions-Interviews\u002Fdp\u002F0994138636\u002F)\n  * 量化金融面试实用指南，作者：周新峰：[Amazon](https:\u002F\u002Fwww.amazon.com\u002FPractical-Guide-Quantitative-Finance-Interviews\u002Fdp\u002F1438236662\u002F)\n\n### - 课程：\n  * 罗伯特·希勒主讲的金融市场（耶鲁大学）：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8FB14A2200B87185)，[Coursera](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Ffinancial-markets-global)\n  * 数学专题及其在金融中的应用（MIT）：[YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63ctJIEC1UnZ0btsphnnoHR)，[课程页面](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-s096-topics-in-mathematics-with-applications-in-finance-fall-2013\u002F)\n\n### - 其他：\n  * 一组骰子问题：[PDF](http:\u002F\u002Fwww.madandmoonly.com\u002Fdoctormatt\u002Fmathematics\u002Fdice1.pdf)\n\n\n\n***\n\n\n## 更多：\n  * 带视频讲座的计算机科学课程：https:\u002F\u002Fgithub.com\u002FDeveloper-Y\u002Fcs-video-courses\n  * 开源数据科学硕士项目：http:\u002F\u002Fdatasciencemasters.org","# FreeML 快速上手指南\n\n> **注意**：FreeML 并非一个可安装的软件包或框架，而是一个由社区维护的**数据科学与机器学习免费学习资源清单**。本指南旨在帮助开发者高效利用该清单规划学习路径，无需执行安装命令。\n\n## 环境准备\n\n由于 FreeML 本身是资源索引，您只需准备以下基础开发环境即可开始学习清单中推荐的课程和实践项目：\n\n*   **操作系统**：Windows, macOS 或 Linux 均可。\n*   **编程语言**：Python 3.x（清单中绝大多数课程和工具基于 Python）。\n*   **前置依赖**：\n    *   建议安装 **Anaconda** 或 **Miniconda** 管理 Python 环境和数据科学包。\n    *   代码编辑器或 IDE（推荐 VS Code 或 PyCharm）。\n    *   稳定的网络连接（用于访问 Coursera, YouTube, Stanford 等外部课程资源）。\n    *   *国内加速建议*：访问 GitHub 资源时若速度较慢，可使用国内镜像站；观看视频课程建议使用 Bilibili 等国内平台搜索对应课程名称（如“吴恩达 机器学习”），通常有搬运字幕版。\n\n## 安装步骤\n\nFreeML **无需安装**。您可以直接通过以下方式获取和使用资源：\n\n1.  **访问仓库**：\n    在浏览器中打开 FreeML 的 GitHub 页面查看完整清单。\n    ```bash\n    # 可选：克隆仓库到本地以便离线查阅 Markdown 文件\n    git clone https:\u002F\u002Fgithub.com\u002Fshujianhero\u002FFreeML.git\n    cd FreeML\n    ```\n\n2.  **配置学习环境**（以推荐的首月计划为例）：\n    根据清单建议，首先搭建 Python 基础环境。\n    ```bash\n    # 创建名为 freeml_env 的虚拟环境\n    conda create -n freeml_env python=3.8\n    \n    # 激活环境\n    conda activate freeml_env\n    \n    # 安装基础数据科学栈 (参考清单中的 Keras\u002FTensorFlow 路径)\n    pip install numpy pandas matplotlib scikit-learn keras tensorflow\n    ```\n\n## 基本使用\n\nFreeML 的核心用法是**按图索骥**，根据您的目标选择对应的学习模块。以下是基于清单内容的三种典型使用场景：\n\n### 场景一：零基础快速入门（一月计划）\n如果您希望在一个月内建立基本概念，请按照 `One Month Plan` 章节执行：\n1.  **Python 基础**：阅读 *Learn Python the Hard Way* 免费在线书。\n2.  **核心理论**：选修 Stanford Statistical Learning 或 吴恩达 (Andrew Ng) 的 Coursera 机器学习课程。\n3.  **深度学习入门**：学习 吴恩达 的 Deep Learning Specialization。\n4.  **实战框架**：阅读 *Keras in 30 sec* 官方文档并运行示例代码。\n5.  **数据库基础**：学习 Stanford Databases 自修课程。\n\n### 场景二：进阶专项学习\n根据目录选择特定领域深入钻研：\n\n*   **自然语言处理 (NLP)**：\n    *   视频：Stanford CS224n (Deep Learning for NLP)。\n    *   书籍：*Speech and Language Processing (3rd ed. draft)*。\n    *   工具：安装 `nltk` 包进行练习。\n    ```python\n    import nltk\n    nltk.download('punkt')\n    from nltk.tokenize import word_tokenize\n    print(word_tokenize(\"FreeML is a great resource list.\"))\n    ```\n\n*   **深度学习 (Deep Learning)**：\n    *   视频：Stanford CS231n (CNN 视觉识别) 或 吴恩达 系列课程。\n    *   书籍：*Deep Learning* by Ian Goodfellow (花书)。\n    *   实践：选择 Keras, TensorFlow 或 PyTorch 其中之一深入掌握。\n\n*   **强化学习 (Reinforcement Learning)**：\n    *   视频：David Silver (UCL) 课程或 UC Berkeley CS 294。\n    *   书籍：*Reinforcement Learning: An Introduction (2nd)*。\n\n### 场景三：面试准备\n在 `Interviews` 章节中，利用提供的链接刷题：\n*   查阅 \"111 Data Science Interview Questions & Detailed Answers\"。\n*   针对 startups 的 40 道机器学习面试题进行模拟。\n*   在 Kaggle 上查看 \"How to finish a Data Challenge\" 的高分 Kernel 代码。\n\n---\n*提示：清单中提到的所有课程链接、PDF 书籍和视频资源，请直接点击原仓库中的超链接访问。对于部分国外网站，建议配合网络工具或使用国内视频平台的转载资源进行学习。*","一名非计算机专业的市场分析师希望转型数据科学，试图在一个月内建立机器学习基础并掌握自然语言处理技能以分析用户评论。\n\n### 没有 FreeML 时\n- **资源筛选困难**：面对网络上海量的教程、视频和书籍，难以分辨哪些适合零基础入门，哪些过于深奥，浪费大量时间试错。\n- **学习路径混乱**：缺乏系统性的规划，不知道应该先学 Python 基础还是直接看统计学理论，导致知识点碎片化，无法形成完整体系。\n- **高昂的试错成本**：容易误入收费昂贵但内容陈旧的课程，或者找到只有理论没有代码实践的“天书”，打击学习信心。\n- **领域覆盖不全**：在关注机器学习时，往往忽略了对后续工作至关重要的 NLP（自然语言处理）或深度学习专项资源，导致技能树偏科。\n\n### 使用 FreeML 后\n- **精准获取免费资源**：直接利用 FreeML 中精选的\"Mostly Free\"列表，快速锁定如《Learn Python the Hard Way》和吴恩达的斯坦福课程等高质量免费教材。\n- **执行清晰月度计划**：参考工具中提供的\"One Month Plan\"，按部就班地从 Python 语法过渡到统计学习，再到 Keras 实战，确保学习节奏张弛有度。\n- **理论与实践平衡**：依据列表中的评论建议，选择既包含视频讲解又配套经典电子书（如 ISL）的课程，确保既能听懂原理又能动手写代码。\n- **全面拓展技能边界**：顺着目录轻松找到 Stanford CS224n 等 NLP 专项课程，在完成机器学习基础后，无缝衔接文本分析技能，满足实际业务需求。\n\nFreeML 通过提供一条经过验证的、低成本且结构清晰的学习路径，帮助非科班出身者高效跨越从兴趣到实战的鸿沟。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FShujian2015_FreeML_cd3a4ee4.png","Shujian2015",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FShujian2015_fca1054a.jpg","Software engineer, Ph.D., and Kaggle triple master. Speech and NLP.","Google","Boston, MA","bagoftricks.ml","https:\u002F\u002Fgithub.com\u002FShujian2015",1130,516,"2026-03-08T15:18:41",1,"","未说明",{"notes":87,"python":85,"dependencies":88},"该 README 并非软件工具的技术文档，而是一份数据科学与机器学习的学习资源清单（包含课程视频、书籍、教程链接等）。文中提到了 Python、Keras、TensorFlow、PyTorch、NLTK 等作为学习内容的技术栈，但未提供具体的安装指南、版本要求或硬件运行环境需求。",[],[16,90,14,35],"其他",[92,93,94,95],"machine-learning","data-science","deep-learning","natural-language-processing","2026-03-27T02:49:30.150509","2026-04-08T22:42:18.741565",[],[]]