[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-aridiosilva--AI_Books":3,"tool-aridiosilva--AI_Books":65},[4,23,32,40,49,57],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":22},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,2,"2026-04-05T10:45:23",[13,14,15,16,17,18,19,20,21],"图像","数据工具","视频","插件","Agent","其他","语言模型","开发框架","音频","ready",{"id":24,"name":25,"github_repo":26,"description_zh":27,"stars":28,"difficulty_score":29,"last_commit_at":30,"category_tags":31,"status":22},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,3,"2026-04-04T04:44:48",[17,13,20,19,18],{"id":33,"name":34,"github_repo":35,"description_zh":36,"stars":37,"difficulty_score":29,"last_commit_at":38,"category_tags":39,"status":22},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74913,"2026-04-05T10:44:17",[19,13,20,18],{"id":41,"name":42,"github_repo":43,"description_zh":44,"stars":45,"difficulty_score":46,"last_commit_at":47,"category_tags":48,"status":22},3215,"awesome-machine-learning","josephmisiti\u002Fawesome-machine-learning","awesome-machine-learning 是一份精心整理的机器学习资源清单，汇集了全球优秀的机器学习框架、库和软件工具。面对机器学习领域技术迭代快、资源分散且难以甄选的痛点，这份清单按编程语言（如 Python、C++、Go 等）和应用场景（如计算机视觉、自然语言处理、深度学习等）进行了系统化分类，帮助使用者快速定位高质量项目。\n\n它特别适合开发者、数据科学家及研究人员使用。无论是初学者寻找入门库，还是资深工程师对比不同语言的技术选型，都能从中获得极具价值的参考。此外，清单还延伸提供了免费书籍、在线课程、行业会议、技术博客及线下聚会等丰富资源，构建了从学习到实践的全链路支持体系。\n\n其独特亮点在于严格的维护标准：明确标记已停止维护或长期未更新的项目，确保推荐内容的时效性与可靠性。作为机器学习领域的“导航图”，awesome-machine-learning 以开源协作的方式持续更新，旨在降低技术探索门槛，让每一位从业者都能高效地站在巨人的肩膀上创新。",72149,1,"2026-04-03T21:50:24",[20,18],{"id":50,"name":51,"github_repo":52,"description_zh":53,"stars":54,"difficulty_score":46,"last_commit_at":55,"category_tags":56,"status":22},2234,"scikit-learn","scikit-learn\u002Fscikit-learn","scikit-learn 是一个基于 Python 构建的开源机器学习库，依托于 SciPy、NumPy 等科学计算生态，旨在让机器学习变得简单高效。它提供了一套统一且简洁的接口，涵盖了从数据预处理、特征工程到模型训练、评估及选择的全流程工具，内置了包括线性回归、支持向量机、随机森林、聚类等在内的丰富经典算法。\n\n对于希望快速验证想法或构建原型的数据科学家、研究人员以及 Python 开发者而言，scikit-learn 是不可或缺的基础设施。它有效解决了机器学习入门门槛高、算法实现复杂以及不同模型间调用方式不统一的痛点，让用户无需重复造轮子，只需几行代码即可调用成熟的算法解决分类、回归、聚类等实际问题。\n\n其核心技术亮点在于高度一致的 API 设计风格，所有估算器（Estimator）均遵循相同的调用逻辑，极大地降低了学习成本并提升了代码的可读性与可维护性。此外，它还提供了强大的模型选择与评估工具，如交叉验证和网格搜索，帮助用户系统地优化模型性能。作为一个由全球志愿者共同维护的成熟项目，scikit-learn 以其稳定性、详尽的文档和活跃的社区支持，成为连接理论学习与工业级应用的最",65628,"2026-04-05T10:10:46",[20,18,14],{"id":58,"name":59,"github_repo":60,"description_zh":61,"stars":62,"difficulty_score":10,"last_commit_at":63,"category_tags":64,"status":22},3364,"keras","keras-team\u002Fkeras","Keras 是一个专为人类设计的深度学习框架，旨在让构建和训练神经网络变得简单直观。它解决了开发者在不同深度学习后端之间切换困难、模型开发效率低以及难以兼顾调试便捷性与运行性能的痛点。\n\n无论是刚入门的学生、专注算法的研究人员，还是需要快速落地产品的工程师，都能通过 Keras 轻松上手。它支持计算机视觉、自然语言处理、音频分析及时间序列预测等多种任务。\n\nKeras 3 的核心亮点在于其独特的“多后端”架构。用户只需编写一套代码，即可灵活选择 TensorFlow、JAX、PyTorch 或 OpenVINO 作为底层运行引擎。这一特性不仅保留了 Keras 一贯的高层易用性，还允许开发者根据需求自由选择：利用 JAX 或 PyTorch 的即时执行模式进行高效调试，或切换至速度最快的后端以获得最高 350% 的性能提升。此外，Keras 具备强大的扩展能力，能无缝从本地笔记本电脑扩展至大规模 GPU 或 TPU 集群，是连接原型开发与生产部署的理想桥梁。",63927,"2026-04-04T15:24:37",[20,14,18],{"id":66,"github_repo":67,"name":68,"description_en":69,"description_zh":70,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":81,"owner_email":82,"owner_twitter":76,"owner_website":83,"owner_url":84,"languages":80,"stars":85,"forks":86,"last_commit_at":87,"license":80,"difficulty_score":46,"env_os":88,"env_gpu":88,"env_ram":88,"env_deps":89,"category_tags":101,"github_topics":80,"view_count":29,"oss_zip_url":80,"oss_zip_packed_at":80,"status":22,"created_at":102,"updated_at":103,"faqs":104,"releases":110},431,"aridiosilva\u002FAI_Books","AI_Books","Books related to  Artificial Intelligence, Machine Learning, Deep Learning and Neural Networks","AI_Books 是一个汇集人工智能领域优质图书资源的开源项目，专注于整理与人工智能、机器学习、深度学习和神经网络相关的免费在线书籍与电子书。它解决了初学者和从业者在浩如烟海的学习资料中难以筛选权威、系统内容的问题，提供了一站式的高质量阅读清单。\n\n这些资源涵盖从数学基础（如线性代数）到主流框架（如 TensorFlow、Keras）的实践应用，既有经典教材如《人工智能：一种现代方法》，也有广受欢迎的在线著作如 Michael Nielsen 的《神经网络与深度学习》和 MIT 出版的《深度学习》。部分书籍还配有 Python 或 R 语言的代码示例，便于边学边练。\n\nAI_Books 特别适合刚入门或希望系统提升理论与实践能力的开发者、学生及研究人员使用。虽然不包含独创性技术，但其价值在于精心筛选和集中归类了社区公认的学习资料，并链接了 Google PAIR 等实用工具平台，帮助用户更高效地进入 AI 领域。整体风格务实清晰，是自学路上的可靠导航。","# Artifical Intelligence & Machine Learning & Deep Learning & Neural Networks Books\nBooks related to  Artificial Intelligence, Machine Learning, Deep Learning and Neural Networks\n\n## Online Books about AI and Deep Learning\n\n- [link to ONLINE Book about Neural Networks and Deep Learning by MIchael Nielsen](http:\u002F\u002Fneuralnetworksanddeeplearning.com\u002F)\n- [link to ONLINE BOOK about DEEP LEARNING of MIT PRESS BOOK](https:\u002F\u002Fwww.deeplearningbook.org\u002F)\n- [link to Tools to Help Tensorflow Development](https:\u002F\u002Fwww.tensorflow.org\u002Fresources\u002Ftools)\n- [link to PAIR code - Code repositories from People+AI Research PAIR Initiative](https:\u002F\u002Fgithub.com\u002FPAIR-code)\n- [link to Tolls & Platoforms + PAIR](https:\u002F\u002Fpair.withgoogle.com\u002Ftools\u002F)\n\n## Math For AI and AI\n\n- [Book - Math for AI - Basics of Linear Algebra for Machine Learning (Examples in Python Code) 212 Pages · 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Math%20for%20AI%20-%20Basics%20of%20Linear%20Algebra%20for%20Machine%20Learning%20(Examples%20in%20Python%20Code)%20212%20Pages%20%C2%B7%202017%20%20(GOOD).pdf)\n- [Book Artificial Intelligence A Modern Approach (3rd Edition) 1154 Pages 2010](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Artificial%20Intelligence%20A%20Modern%20Approach%20(3rd%20Edition)%201154%20Pages%202010.pdf)\n\n## Deep Learning\n\n- [Book - Deep Learning - MIT PRESS - Book Online 2019](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Deep%20Learning%20-%20MIT%20PRESS%20-%20Book%20Online%202019.pdf)\n- [Book Deep Learning - Fundamentals, Theory and Applications 168 Pages 2019](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20-%20Fundamentals%2C%20Theory%20and%20Applications%20168%20Pages%202019.pdf)\n- [Book Deep Learning with Appls Using Python - Tensorflow and Keras - Chatbots, Object and Speech Recognition 227 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20Appls%20Using%20Python%20-%20Tensorflow%20and%20Keras%20-%20Chatbots%2C%20Object%20and%20Speech%20Recognition%20227%20Pages%202018.pdf)\n- [Book Deep Learning with Python 386 Pages 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20Python%20386%20Pages%202017.pdf)\n- [Book Deep Learning with R 341 Pages 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20R%20341%20Pages%202017.pdf)\n- [Book Deep learning - Adaptive Computation and Machine Learning 801 Pages 2016](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20learning%20-%20Adaptive%20Computation%20and%20Machine%20Learning%20801%20Pages%202016.pdf)\n- [Book Unsupervised Deep Learning in Python 100 Pages 2016](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Unsupervised%20Deep%20Learning%20in%20Python%20100%20Pages%202016.pdf)\n\n## Neural Networks\n\n- [Book - Neural Networks and Deep Learning - Michael Nielsen - 281 pages Oct 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Neural%20Networks%20and%20Deep%20Learning%20-%20Michael%20Nielsen%20-%20281%20pages%20Oct%202018%20.pdf)\n- [Book Learn Keras for Deep Neural Networks - A Fast-Track Approach with Python 192 Pages 2019](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learn%20Keras%20for%20Deep%20Neural%20Networks%20-%20A%20Fast-Track%20Approach%20with%20Python%20192%20Pages%202019.pdf)\n- [Book Convolutional Neural Networks in Python 75 Pages 2016](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Convolutional%20Neural%20Networks%20in%20Python%2075%20Pages%202016.pdf)\n- [Book Convolutional Neural Networks in Visual Computing 187 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Convolutional%20Neural%20Networks%20in%20Visual%20Computing%20187%20Pages%202018.pdf)\n\n## Tensor Flow\n\n- [Book Learning Tensorflow - A Guide to Building Deep Learning Systems 242 Pages 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learning%20Tensorflow%20-%20A%20Guide%20to%20Building%20Deep%20Learning%20Systems%20242%20Pages%202017.pdf)\n- [Book - TensorFlow - Getting Started With TensorFlow 178 Pages](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20TensorFlow%20-%20Getting%20Started%20With%20TensorFlow%20178%20Pages%20%C2%B7%202016.pdf)\n\n## Machine Learning\n\n- [Book Machine Learning with Python Cookbook - Practical Solutions 366 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Machine%20Learning%20with%20Python%20Cookbook%20-%20Practical%20Solutions%20366%20Pages%202018.pdf)\n- [Book Reinforcement Learning - With Open AI, TensorFlow and Keras Using Python 174 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Reinforcement%20Learning%20-%20With%20Open%20AI%2C%20TensorFlow%20and%20Keras%20Using%20Python%20174%20Pages%202018.pdf)\n- [Book Guide to Convolutional Neural Networks - Traffic-Sign Detection and Classification 303 Pages 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Guide%20to%20Convolutional%20Neural%20Networks%20-%20Traffic-Sign%20Detection%20and%20Classification%20303%20Pages%202017.pdf)\n\n## Data Science And Big Data\n\n- [Book Big Data SMACK - A Guide to Apache Spark, Mesos, Akka, Cassandra, and Kafka 277 Pages 2016](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Big%20Data%20SMACK%20-%20A%20Guide%20to%20Apache%20Spark%2C%20Mesos%2C%20Akka%2C%20Cassandra%2C%20and%20Kafka%20277%20Pages%202016.pdf)\n- [Book Spark - The Definitive Guide - Big Data Processing Made Simple 601 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Spark%20-%20The%20Definitive%20Guide%20-%20Big%20Data%20Processing%20Made%20Simple%20601%20Pages%202018.pdf)\n- [Book Data Analysis From Scratch With Python, Pandas, NumPy, Scikit-Learn, IPython, TensorFlow and Matplotlib 104 pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Data%20Analysis%20From%20Scratch%20With%20Python%2C%20Pandas%2C%20NumPy%2C%20Scikit-Learn%2C%20IPython%2C%20TensorFlow%20and%20Matplotlib%20104%20pages%202018.pdf)\n- [Book Advanced Data Analytics Using Python - With Machine Learning, Deep Learning and NLP Examples 195 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Advanced%20Data%20Analytics%20Using%20Python%20-%20With%20Machine%20Learning%2C%20Deep%20Learning%20and%20NLP%20Examples%20195%20Pages%202018.pdf)\n- [Book Practical Data Science with R 417 Pages 2014](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Practical%20Data%20Science%20with%20R%20417%20Pages%202014.pdf)\n\n## R and Data Science\n\n- [Book R in Action - Data analysis and graphics with R 474 Pages 2011](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20%20R%20in%20Action%20-%20Data%20analysis%20and%20graphics%20with%20R%20474%20Pages%202011.pdf)\n- [Book Learn R for Applied Statistics - With Data Visualizations, Regressions, and Statistics 254 Pages 2019](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learn%20R%20for%20Applied%20Statistics%20-%20With%20Data%20Visualizations%2C%20Regressions%2C%20and%20Statistics%20254%20Pages%202019.pdf)\n- [Book R Markdown - The Definitive Guide 339 Pages 2018](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20R%20Markdown%20-%20The%20Definitive%20Guide%20339%20Pages%202018.pdf)\n\n## MathLab and Deep Learning\n\n- [Book MATLAB Deep Learning - With Machine Learning, Neural Networks and Artificial Intelligence 162 Pages 2017](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20MATLAB%20Deep%20Learning%20-%20With%20Machine%20Learning%2C%20Neural%20Networks%20and%20Artificial%20Intelligence%20162%20Pages%202017.pdf)\n\n\n# Linear Algebra Algorithms Video Tutorials -  Numerical Computing with Python\n\n### Gauss Elimination Method with Pivoting \n\nIn this tutorial, the basic steps of Gauss Elimination (or Gaussian Elimination) method to solve  a system of linear equations are explained in details with examples, algorithms and Python codes. Gauss elimination (after Carl Friedrich Gauss, 1777-1855) is a the basis of all other elimination methods applied to solve systems of linear equations.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZDxONtacA_4)\n- [Part 2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=i7f9PBe-j_Y)\n\n## Cholesky Factorization Method - Decomposition \n\nIn this video, Cholesky factorization method (after André-Louis Cholesky) is explained with examples. The tutorial includes the definitions of the LU-decomposition and Cholesky decomposition, the conditions of Cholesky decomposition, the use of Numpy eigenvalue functions to test the positive definiteness, the derivation of Cholesky algorithm and Coding in Python.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4SWMzENcgSE)\n- [Part 2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qNKyw5ED7eM)\n\n## Gauss-Jordan Method Tutorial - Step-By-Step Theory & Coding\n\nIn this tutorial, the procedure of Gauss-Jordan elimination method is explained step-by-step using symbolic and numeric examples. The general formulas and Gauss-Jordan algorithm are applied to write a Python code to solve the numeric example.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xOLJMKGNivU)\n\n## Lagrange Interpolation Method: Algorithm, Computation and Plot\nLagrange interpolation (or Lagrangian interpolation) method is one of the most basic and common methods to apply the interpolation polynomials. It was named after the great mathematician Joseph-Louis Lagrange (1736-1813). This tutorial explains the Lagrangian polynomial form of the interpolation function, the algorithm of the method and the Python code by using Python lists with basic for loops and by using the Numpy arrays by using conditional slicing in addition to plotting the interpolation function versus the given data points by using matplotlib.pyplot module.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dTGqOj1NZwY)\n\n## Binomial Distributions - Probabilities of Probabilities\n\nThe binomial distribution consists of the probabilities of each of the possible numbers of successes on N trials for independent events that each have a probability of π (the Greek letter pi) of occurring. For the coin flip example, N = 2 and π = 0.5.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8idr1WZ1A7Q)\n- [Part 2](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZA4JkHKZM50&t=0s)\n\n## Normal Distribution & Probability Problems\n\nThis calculus video tutorial provides a basic introduction into normal distribution and probability.  It explains how to solve normal distribution problems using a simple chart and using calculus by evaluating the definite integral of the probability density function for a bell shaped curve or normal distribution curve.  This video contains 1 practice problem in the form of a word problem with many parts giving you plenty of examples to master this topic.  In this video, I explain how to evaluate the definite integral using wolfram's alpha online calculator for definite integrals.  You need to determine the population mean mu and standard deviation sigma as well as the lower and upper limits of integration in order to determine the probability of an event occurring within a certain range of X values where X is a continuous random variable.  You need to be familiar with the 68-95-99.7 rule.  Approximately 68% of the population lies within 1 standard deviation of the population mean or average.  95% of the population lies within 2 standard deviations of the mean and 99.7% lies within 3 standard deviations of the mean.\n\n- [Part 1](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=gHBL5Zau3NE)\n\n\n","# 人工智能（Artificial Intelligence, AI）、机器学习（Machine Learning）、深度学习（Deep Learning）与神经网络（Neural Networks）相关书籍\n\n与人工智能、机器学习、深度学习和神经网络相关的书籍资源。\n\n## 关于 AI 与深度学习的在线书籍\n\n- [Michael Nielsen 所著《神经网络与深度学习》在线书籍链接](http:\u002F\u002Fneuralnetworksanddeeplearning.com\u002F)\n- [MIT Press 出版的《深度学习》在线书籍链接](https:\u002F\u002Fwww.deeplearningbook.org\u002F)\n- [TensorFlow 开发辅助工具链接](https:\u002F\u002Fwww.tensorflow.org\u002Fresources\u002Ftools)\n- [PAIR 代码库 —— 来自 People+AI Research (PAIR) 倡议的代码仓库](https:\u002F\u002Fgithub.com\u002FPAIR-code)\n- [PAIR 工具与平台链接](https:\u002F\u002Fpair.withgoogle.com\u002Ftools\u002F)\n\n## AI 所需的数学基础\n\n- [《AI 数学基础：面向机器学习的线性代数基础（含 Python 代码示例）》，212 页，2017 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Math%20for%20AI%20-%20Basics%20of%20Linear%20Algebra%20for%20Machine%20Learning%20(Examples%20in%20Python%20Code)%20212%20Pages%20%C2%B7%202017%20%20(GOOD).pdf)\n- [《人工智能：一种现代方法（第 3 版）》，1154 页，2010 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Artificial%20Intelligence%20A%20Modern%20Approach%20(3rd%20Edition)%201154%20Pages%202010.pdf)\n\n## 深度学习\n\n- [《深度学习》— MIT Press，在线版，2019 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Deep%20Learning%20-%20MIT%20PRESS%20-%20Book%20Online%202019.pdf)\n- [《深度学习：基础、理论与应用》，168 页，2019 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20-%20Fundamentals%2C%20Theory%20and%20Applications%20168%20Pages%202019.pdf)\n- [《使用 Python 进行深度学习应用开发 —— TensorFlow 与 Keras 实现聊天机器人、目标识别与语音识别》，227 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20Appls%20Using%20Python%20-%20Tensorflow%20and%20Keras%20-%20Chatbots%2C%20Object%20and%20Speech%20Recognition%20227%20Pages%202018.pdf)\n- [《Python 深度学习》，386 页，2017 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20Python%20386%20Pages%202017.pdf)\n- [《R 语言深度学习》，341 页，2017 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20Learning%20with%20R%20341%20Pages%202017.pdf)\n- [《深度学习 — 自适应计算与机器学习系列》，801 页，2016 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Deep%20learning%20-%20Adaptive%20Computation%20and%20Machine%20Learning%20801%20Pages%202016.pdf)\n- [《Python 中的无监督深度学习》，100 页，2016 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Unsupervised%20Deep%20Learning%20in%20Python%20100%20Pages%202016.pdf)\n\n## 神经网络\n\n- [《神经网络与深度学习》— Michael Nielsen，281 页，2018 年 10 月](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20Neural%20Networks%20and%20Deep%20Learning%20-%20Michael%20Nielsen%20-%20281%20pages%20Oct%202018%20.pdf)\n- [《快速掌握 Keras 构建深度神经网络 — 使用 Python 的高效入门方法》，192 页，2019 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learn%20Keras%20for%20Deep%20Neural%20Networks%20-%20A%20Fast-Track%20Approach%20with%20Python%20192%20Pages%202019.pdf)\n- [《Python 中的卷积神经网络》，75 页，2016 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Convolutional%20Neural%20Networks%20in%20Python%2075%20Pages%202016.pdf)\n- [《视觉计算中的卷积神经网络》，187 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Convolutional%20Neural%20Networks%20in%20Visual%20Computing%20187%20Pages%202018.pdf)\n\n## TensorFlow\n\n- [《学习 TensorFlow：构建深度学习系统的指南》，242 页，2017 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learning%20Tensorflow%20-%20A%20Guide%20to%20Building%20Deep%20Learning%20Systems%20242%20Pages%202017.pdf)\n- [《TensorFlow 入门指南》，178 页，2016 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20-%20TensorFlow%20-%20Getting%20Started%20With%20TensorFlow%20178%20Pages%20%C2%B7%202016.pdf)\n\n## 机器学习\n\n- [《Python 机器学习实战手册：实用解决方案》，366 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Machine%20Learning%20with%20Python%20Cookbook%20-%20Practical%20Solutions%20366%20Pages%202018.pdf)\n- [《强化学习：使用 Python 结合 Open AI、TensorFlow 与 Keras》，174 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Reinforcement%20Learning%20-%20With%20Open%20AI%2C%20TensorFlow%20and%20Keras%20Using%20Python%20174%20Pages%202018.pdf)\n- [《卷积神经网络指南：交通标志检测与分类》，303 页，2017 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Guide%20to%20Convolutional%20Neural%20Networks%20-%20Traffic-Sign%20Detection%20and%20Classification%20303%20Pages%202017.pdf)\n\n## 数据科学与大数据\n\n- [《大数据 SMACK：Apache Spark、Mesos、Akka、Cassandra 与 Kafka 指南》，277 页，2016 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Big%20Data%20SMACK%20-%20A%20Guide%20to%20Apache%20Spark%2C%20Mesos%2C%20Akka%2C%20Cassandra%2C%20and%20Kafka%20277%20Pages%202016.pdf)\n- [《Spark 权威指南：简化大数据处理》，601 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Spark%20-%20The%20Definitive%20Guide%20-%20Big%20Data%20Processing%20Made%20Simple%20601%20Pages%202018.pdf)\n- [《从零开始的数据分析：使用 Python、Pandas、NumPy、Scikit-Learn、IPython、TensorFlow 与 Matplotlib》，104 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Data%20Analysis%20From%20Scratch%20With%20Python%2C%20Pandas%2C%20NumPy%2C%20Scikit-Learn%2C%20IPython%2C%20TensorFlow%20and%20Matplotlib%20104%20pages%202018.pdf)\n- [《使用 Python 进行高级数据分析：含机器学习、深度学习与自然语言处理（NLP）实例》，195 页，2018 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Advanced%20Data%20Analytics%20Using%20Python%20-%20With%20Machine%20Learning%2C%20Deep%20Learning%20and%20NLP%20Examples%20195%20Pages%202018.pdf)\n- [《R 语言实用数据科学》，417 页，2014 年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Practical%20Data%20Science%20with%20R%20417%20Pages%202014.pdf)\n\n## R 与数据科学（Data Science）\n\n- [《R语言实战：R语言的数据分析与图形》（R in Action - Data analysis and graphics with R），474页，2011年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20%20R%20in%20Action%20-%20Data%20analysis%20and%20graphics%20with%20R%20474%20Pages%202011.pdf)\n- [《应用统计学中的R语言学习》（Learn R for Applied Statistics - With Data Visualizations, Regressions, and Statistics），254页，2019年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20Learn%20R%20for%20Applied%20Statistics%20-%20With%20Data%20Visualizations%2C%20Regressions%2C%20and%20Statistics%20254%20Pages%202019.pdf)\n- [《R Markdown：权威指南》（R Markdown - The Definitive Guide），339页，2018年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20R%20Markdown%20-%20The%20Definitive%20Guide%20339%20Pages%202018.pdf)\n\n## MATLAB 与深度学习（Deep Learning）\n\n- [《MATLAB 深度学习：含机器学习、神经网络与人工智能》（MATLAB Deep Learning - With Machine Learning, Neural Networks and Artificial Intelligence），162页，2017年](https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fblob\u002Fmaster\u002FBook%20MATLAB%20Deep%20Learning%20-%20With%20Machine%20Learning%2C%20Neural%20Networks%20and%20Artificial%20Intelligence%20162%20Pages%202017.pdf)\n\n\n# 线性代数算法视频教程 - 使用 Python 进行数值计算（Numerical Computing with Python）\n\n### 带主元选取的高斯消元法（Gauss Elimination Method with Pivoting）\n\n本教程详细讲解了高斯消元法（Gauss Elimination，又称 Gaussian Elimination）求解线性方程组的基本步骤，并配有示例、算法和 Python 代码。高斯消元法（以卡尔·弗里德里希·高斯 Carl Friedrich Gauss，1777–1855 命名）是所有用于求解线性方程组的消元方法的基础。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZDxONtacA_4)\n- [第二部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=i7f9PBe-j_Y)\n\n## Cholesky 分解法（Cholesky Factorization Method - Decomposition）\n\n本视频讲解了 Cholesky 分解法（以 André-Louis Cholesky 命名），并配有示例。教程内容包括 LU 分解与 Cholesky 分解的定义、Cholesky 分解的适用条件、使用 NumPy 特征值函数检验矩阵正定性、Cholesky 算法的推导以及 Python 编码实现。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4SWMzENcgSE)\n- [第二部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=qNKyw5ED7eM)\n\n## 高斯-若尔当消元法教程（Gauss-Jordan Method Tutorial）- 分步理论与编码\n\n本教程通过符号和数值示例，逐步讲解高斯-若尔当消元法（Gauss-Jordan elimination method）的求解过程。教程将通用公式和 Gauss-Jordan 算法应用于编写 Python 代码，以求解数值示例。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=xOLJMKGNivU)\n\n## 拉格朗日插值法（Lagrange Interpolation Method）：算法、计算与绘图\n\n拉格朗日插值法（Lagrange interpolation，或称 Lagrangian interpolation）是最基础且常用的多项式插值方法之一，以著名数学家约瑟夫-路易·拉格朗日（Joseph-Louis Lagrange，1736–1813）命名。本教程讲解了插值函数的拉格朗日多项式形式、该方法的算法，并展示了两种 Python 实现方式：一种使用 Python 列表配合基础 for 循环，另一种使用 NumPy 数组配合条件切片。此外，还使用 matplotlib.pyplot 模块绘制了插值函数与给定数据点的对比图。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=dTGqOj1NZwY)\n\n## 二项分布（Binomial Distributions）- “概率的概率”\n\n二项分布包含在 N 次独立试验中，每次试验成功概率为 π（希腊字母 pi）时，各种可能成功次数所对应的概率。以抛硬币为例，N = 2，π = 0.5。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=8idr1WZ1A7Q)\n- [第二部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ZA4JkHKZM50&t=0s)\n\n## 正态分布与概率问题（Normal Distribution & Probability Problems）\n\n本微积分视频教程对正态分布和概率进行了基础介绍。它解释了如何使用简单查表法和微积分方法（即计算钟形曲线或正态分布曲线的概率密度函数的定积分）来求解正态分布问题。本视频包含一道综合应用题（word problem），分为多个小问，为你提供充足的示例以掌握该主题。视频中还演示了如何使用 Wolfram Alpha 在线计算器计算定积分。你需要确定总体均值（mu）和标准差（sigma），以及积分的上下限，从而计算连续型随机变量 X 在某一取值范围内事件发生的概率。你还需要熟悉 68-95-99.7 法则：大约 68% 的数据落在总体均值的一个标准差范围内，95% 落在两个标准差内，99.7% 落在三个标准差内。\n\n- [第一部分](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=gHBL5Zau3NE)","# AI_Books 快速上手指南\n\n## 环境准备\n\nAI_Books 是一个开源的 AI\u002FML\u002FDL 相关书籍与学习资源集合，**无需安装运行环境**，仅需以下任一方式访问内容：\n\n- **本地阅读 PDF**：需安装 PDF 阅读器（如 Adobe Acrobat、SumatraPDF 或浏览器内置阅读器）\n- **在线阅读**：使用现代浏览器（Chrome \u002F Edge \u002F Firefox 最新版）\n- **可选开发环境**（若需运行书中代码示例）：\n  - Python ≥ 3.6\n  - 推荐使用 [清华源](https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\u002F) 加速依赖安装：\n    ```bash\n    pip config set global.index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\u002F\n    ```\n\n## 安装步骤\n\n本项目为纯资源仓库，通过 Git 克隆即可获取全部书籍与链接：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books.git\n```\n\n> 国内用户建议使用加速镜像（如有）或直接访问 GitHub 页面浏览。\n\n## 基本使用\n\n### 1. 浏览在线书籍\n直接访问 README 中提供的在线链接，例如：\n- [Neural Networks and Deep Learning（Michael Nielsen）](http:\u002F\u002Fneuralnetworksanddeeplearning.com\u002F)\n- [Deep Learning Book（MIT Press）](https:\u002F\u002Fwww.deeplearningbook.org\u002F)\n\n### 2. 阅读本地 PDF\n进入克隆后的目录，用 PDF 阅读器打开所需书籍，例如：\n```bash\n# 示例：阅读《Deep Learning with Python》\ncd AI_Books\nopen \"Book Deep Learning with Python 386 Pages 2017.pdf\"  # macOS\n# 或\nxdg-open \"Book Deep Learning with Python 386 Pages 2017.pdf\"  # Linux\n# Windows 用户可直接双击文件\n```\n\n### 3. 查看视频教程\n点击对应 YouTube 链接观看线性代数与数值计算教程（如高斯消元法、Cholesky 分解等），建议配合书中数学基础章节学习。\n\n> 提示：所有资源均为免费开源，适合 AI 初学者与进阶开发者系统学习。","某高校计算机系研究生小李正在准备毕业课题——基于卷积神经网络的医学影像分割系统，但缺乏系统性的深度学习与TensorFlow实战资料。\n\n### 没有 AI_Books 时\n- 需在多个搜索引擎和论坛中零散查找AI教材，耗费大量时间筛选可靠资源  \n- 对卷积神经网络（CNN）原理理解不深，难以将理论应用到医学图像任务中  \n- 缺乏结合Python和TensorFlow的实战书籍，调试模型时常因基础不牢而卡壳  \n- 数学基础薄弱，线性代数与梯度计算等概念模糊，影响模型调优效率  \n\n### 使用 AI_Books 后\n- 通过AI_Books快速定位《Convolutional Neural Networks in Python》和《Deep Learning with Python》，直接获取针对性强的实战指南  \n- 借助Michael Nielsen的《Neural Networks and Deep Learning》深入理解CNN底层机制，有效改进网络结构设计  \n- 利用《Learning Tensorflow》一书系统掌握框架使用技巧，显著减少环境配置和代码调试时间  \n- 参考《Basics of Linear Algebra for Machine Learning》补足数学短板，提升对损失函数和反向传播的理解  \n\nAI_Books将分散、高门槛的AI学习资源集中整合，让开发者从“找资料”转向“做项目”，大幅缩短从理论到实践的路径。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Faridiosilva_AI_Books_279773f5.png","aridiosilva","Aridio Silva","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Faridiosilva_01f63bed.jpg","I'm a senior software developer and  started my career in 1977.  Since then I've never left. I'm still in love with it.",null,"São Paulo, Brazil","aridiosilva@aridiosilva.com","https:\u002F\u002Fbr.linkedin.com\u002Fpub\u002Faridio-silva\u002F11\u002F971\u002F749","https:\u002F\u002Fgithub.com\u002Faridiosilva",696,163,"2026-04-04T10:44:24","未说明",{"notes":90,"python":88,"dependencies":91},"该仓库主要提供人工智能、机器学习、深度学习等相关领域的电子书和在线资源链接，并包含部分Python代码示例和数学算法视频教程。不涉及具体可执行程序，因此无明确运行环境要求。部分书籍内容涉及TensorFlow、Keras、R和MATLAB等工具的使用，实际环境需求取决于读者运行书中代码的具体情况。",[92,93,94,95,96,97,98,99,100],"TensorFlow","Keras","NumPy","Pandas","Scikit-Learn","Matplotlib","IPython","R","MATLAB",[18],"2026-03-27T02:49:30.150509","2026-04-06T06:46:05.124936",[105],{"id":106,"question_zh":107,"answer_zh":108,"source_url":109},1647,"PDF 版本中的公式渲染效果差，难以理解，怎么办？","该仓库并非原作者维护的官方仓库，因此无法修复 PDF 渲染问题。建议直接访问网页版阅读内容（注意浏览器可能因网站缺少证书而阻止加载）。若需高质量公式显示，请优先使用 HTML 版本。","https:\u002F\u002Fgithub.com\u002Faridiosilva\u002FAI_Books\u002Fissues\u002F1",[]]