[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-d0r1h--ML-University":3,"similar-d0r1h--ML-University":56},{"id":4,"github_repo":5,"name":6,"description_en":7,"description_zh":8,"ai_summary_zh":8,"readme_en":9,"readme_zh":10,"quickstart_zh":11,"use_case_zh":12,"hero_image_url":13,"owner_login":14,"owner_name":15,"owner_avatar_url":16,"owner_bio":17,"owner_company":17,"owner_location":17,"owner_email":17,"owner_twitter":17,"owner_website":17,"owner_url":18,"languages":17,"stars":19,"forks":20,"last_commit_at":21,"license":17,"difficulty_score":22,"env_os":23,"env_gpu":24,"env_ram":24,"env_deps":25,"category_tags":28,"github_topics":33,"view_count":50,"oss_zip_url":17,"oss_zip_packed_at":17,"status":51,"created_at":52,"updated_at":53,"faqs":54,"releases":55},7322,"d0r1h\u002FML-University","ML-University","Machine Learning Open Source University","ML-University 是一个面向机器学习爱好者的开源免费学习平台，旨在汇聚全球优质教育资源，构建一座没有围墙的“机器大学”。它解决了初学者在面对海量且分散的 AI 学习资料时难以系统入门、缺乏权威指引的痛点。\n\n该项目通过精心整理的分类目录，涵盖了从数学基础（如线性代数、统计学）、机器学习与深度学习核心原理，到自然语言处理、强化学习乃至前沿的大语言模型（LLM）和量子机器学习等全栈知识体系。除了理论课程，ML-University 还特别提供了生产环境部署、经典论文研读、数据集资源以及各大科技公司技术博客等实战内容，帮助学习者打通从理论到应用的最后一公里。\n\n无论是零基础的普通用户、希望系统提升技能的开发者，还是从事前沿探索的研究人员，都能在这里找到适合自己的学习路径。其独特亮点在于持续更新的社区协作模式，不仅收录了哈佛、MIT、斯坦福等名校公开课，还整合了 fast.ai 等业界实战教程，确保内容既具学术深度又贴合工业界需求。加入 ML-University，意味着你获得了一位随时在线的博学导师，陪伴你在人工智能领域不断成长。","\u003Cp align=\"center\">\n    \u003Cbr>\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fd0r1h_ML-University_readme_98fd49d3dd3f.png\" width=\"300\"\u002F>\n    \u003Cbr>\n\u003Cp>\n\n\u003Cp align=\"center\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fd0r1h_ML-University_readme_f972e089748d.png\">\n\u003Ca href=\"https:\u002F\u002Ftwitter.com\u002Fintent\u002Ftweet?text=Checkout this awesome Machine Learning University Repo on Github text:&url=https%3A%2F%2Fgithub.com%2Fd0r1h%2FML-University\">\u003Cimg alt=\"tweet\" src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl?style=social&url=https%3A%2F%2Fgithub.com%2Fd0r1h%2FML-University\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">\n    \u003Cp>A Free Machine Learning University \u003C\u002Fp>\n\u003C\u002Fh3>\n\u003Cbr>\n\nMachine Learning Open Source University is an IDEA of free-learning of a ML enthusiast for all other ML enthusiast\n\n**This list is continuously updated** - And if you are a Ml practitioner and have some good suggestions to improve this or have somegood resources to share, you create pull request and contribute.\n\n\n**Table of Contents**\n\n1. [Getting Started](#getting-started)\n2. [Mathematics](#mathematics)\n3. [Machine Learning](#machine-learning)\n4. [Deep Learning](#deep-learning)\n5. [Natural language processing](#natural-language-processing)\n6. [Reinforcement learning](#reinforcement-learning)\n7. [LLM](#large-language-model)\n8. [Books](#books)\n9. [ML in Production](#ml-in-production)\n10. [Quantum ML](#quantum-ml)\n11. [DataSets](#datasets)\n12. [Other Useful Websites](#other-useful-websites)\n13. [Other Useful GitRrpo](#other-useful-gitrepo)\n14. [Blogs and Webinar](#blogs-and-webinar) \n15. [Must Read Research Paper](#must-read-research-paper)\n16. [Company Tech Blogs](#company-tech-blogs)\n17. [Practice Machine Learning](#practice-machine-learning)\n\n\n\n\n\n\n\n\n\n## Getting Started\n\n | Title and Source                                             | Link                               \t\t\t\t          |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | Elements of AI :  Part-1                                     | [WebSite](https:\u002F\u002Fcourse.elementsofai.com\u002F)\t\t\t\t  |\n | Elements of AI :  Part-2                                     | [WebSite](https:\u002F\u002Fbuildingai.elementsofai.com\u002F) \t\t\t  |\n | CS50’s Introduction to AI\t**Harvard**\t\t\t            | [Cs50 WebSite](https:\u002F\u002Fcs50.harvard.edu\u002Fai\u002F2020\u002F)\t\t\t  |\n | Intro to Computational Thinking and Data Science **MIT**     | [WebSite](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-0002-introduction-to-computational-thinking-and-data-science-fall-2016\u002F)\n | Practical Data Ethics\t\t\t\t\t\t\t\t\t\t| [fast.ai](https:\u002F\u002Fethics.fast.ai\u002F)\n | Machine learning Mastery Getting Started \t\t\t\t\t| [machinelearningmastery](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F)\n | Design and Analysis of Algorithms **MIT**\t\t\t\t\t| [ocw.mit.edu](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-046j-design-and-analysis-of-algorithms-spring-2015\u002F)\n | AI: Principles and Techniques **Stanford** \t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rO1NB9TD4iUZ3qghGEGtqNX)|\n | The Private AI Series \t\t\t\t\t\t\t\t\t\t| [openmined](https:\u002F\u002Fcourses.openmined.org\u002Fcourses)|\n\n \n\n## Mathematics\n\n\n | Title and Source                                             | Link                               \t\t\t\t          |\n |------------------------------------------------------------  | -------------------------------------------------------------\n | Statistics in Machine Learning (Krish Naik)                  | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZoTAELRMXVMhVyr3Ri9IQ-t5QPBtxzJO)\n | Computational Linear Algebra for Coders\t\t\t\t\t\t| [fast.ai](https:\u002F\u002Fgithub.com\u002Ffastai\u002Fnumerical-linear-algebra\u002Fblob\u002Fmaster\u002FREADME.md)\n | Linear Algebra  **MIT**\t\t\t\t\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fopenlearninglibrary.mit.edu\u002Fcourses\u002Fcourse-v1:OCW+18.06SC+2T2019\u002Fcourse\u002F)|\n | Statistics by zstatistics\t\t\t\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fwww.zstatistics.com\u002Fvideos)|\n | Essence of linear algebra by 3Blue1Brown\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)|\n | SEEING THEORY (Visual Probability)\t**brown**    \t\t    | [WebSite](https:\u002F\u002Fseeing-theory.brown.edu\u002Fbasic-probability\u002Findex.html)|\n | Matrix Methods in Data Analysis,and Machine Learning **MIT** | [WebSite](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-065-matrix-methods-in-data-analysis-signal-processing-and-machine-learning-spring-2018\u002F)\n | Math for Machine Learning \t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?app=desktop&list=PLD80i8An1OEGZ2tYimemzwC3xqkU0jKUg) |\n | Statistics for Applications **MIT** | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP60uVBMaoNERc6knT_MgPKS0) \n | Introduction to Mathematical Thinking | [Website](http:\u002F\u002Fimt-decal.org\u002F)|\n\n\n\n## Machine Learning\n\n | Title and Source                                             | Link                               \t\t\t\t           |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | Introduction to Machine Learning with scikit-learn \t\t\t| [dataschool](https:\u002F\u002Fcourses.dataschool.io\u002Fintroduction-to-machine-learning-with-scikit-learn)|\n | Introduction to Machine Learning\t\t\t\t\t\t\t\t| [sebastianraschka](https:\u002F\u002Fsebastianraschka.com\u002Fblog\u002F2021\u002Fml-course.html)\n | Open Machine Learning Course \t\t\t\t\t\t\t\t| [mlcourse.ai](https:\u002F\u002Fmlcourse.ai\u002F)\t\t\t\t\t\t   |\n | Machine Learning (CS229) **Stanford**\t\t\t\t\t\t| [WebSite](http:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus-spring2020.html) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU)|\n | Introduction to Machine Learning **MIT** \t\t\t\t\t| [WebSite](https:\u002F\u002Ftinyurl.com\u002Fybl6udcr)\t\t\t\t\t   |\n | Machine Learning Systems Design 2021 (CS329S) **Stanford**   | [WebSite](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html)   |\n | Applied Machine Learning 2020 (CS5787) **Cornell Tech**      | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83)\n | Machine Learning for Healthcare **MIT** \t\t\t\t\t\t| [WebSite](https:\u002F\u002Ftinyurl.com\u002Fyxgeesdf)\t\t\t\t\t   |\n | Machine Learning for Trading **Georgia Tech**\t\t\t\t| [WebSite](https:\u002F\u002Flucylabs.gatech.edu\u002Fml4t\u002F)\t\t\t\t   |\t\n | Introduction to Machine Learning for Coders\t\t\t\t\t| [fast.ai](https:\u002F\u002Fcourse18.fast.ai\u002Fml.html)\n | Machine Learning Crash Course\t\t\t\t\t\t\t\t| [Google AI](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course)|\n | Machine Learning with Python \t\t\t\t\t\t\t\t| [freecodecamp](https:\u002F\u002Fwww.freecodecamp.org\u002Flearn\u002Fmachine-learning-with-python\u002F)|\n | Deep Reinforcement Learning:CS285 **UC Berkeley**\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_iWQOsE6TfURIIhCrlt-wj9ByIVpbfGc)|\n | Probabilistic Machine Learning **University of Tübingen**    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd)|\n | Machine Learning with Graphs(CS224W) **Stanford** \t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rPLKxIpqhjhPgdQy7imNkDn)|\n | Machine Learning in Production **CMU**\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fckaestne.github.io\u002Fseai\u002F)|\n | Machine Learning & Deep Learning Fundamentals                | [deeplizard](https:\u002F\u002Fdeeplizard.com\u002Flearn\u002Fvideo\u002FgZmobeGL0Yg)|\n | Interpretability and Explainability in Machine Learning      | [WebSite](https:\u002F\u002Finterpretable-ml-class.github.io\u002F)|\n | Practical Machine Learning 2021 **Stanford**\t\t\t\t\t| [WebSite](https:\u002F\u002Fc.d2l.ai\u002Fstanford-cs329p\u002Findex.html#)|\n | Machine Learning **VU University** \t\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fmlvu.github.io\u002F)|\n | Machine Learning for Cyber Security **Purdue University**    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL74sw1ohGx7GHqDHCkXZeqMQBVUTMrVLE)|\n | Audio Signal Processing for Machine Learning \t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL-wATfeyAMNqIee7cH3q1bh4QJFAaeNv0)|\n | Machine learning & causal inference **Stanford**\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLxq_lXOUlvQAoWZEqhRqHNezS30lI49G-)|\n | Machine learning cs156 **caltech**                           | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLD63A284B7615313A) |\n | Multimodal machine learning (MMML) **CMU**                   | [WebSite](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-course\u002Ffall2020\u002F)  [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL-Fhd_vrvisNup9YQs_TdLW7DQz-lda0G) | \n | Advanced Topics in Machine Learning **Caltech**              | [WebSite](https:\u002F\u002F1five9.github.io\u002F)\n\n \t\n\n## Deep Learning\n \n \n | Title and Source                                             | Link                               \t\t\t\t           |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | Introduction to Deep Learning(6.S191) **MIT**\t\t \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI)\t\t\t\t\t   |\n | Introduction to Deep Learning\t\t\t\t\t\t\t\t| [sebastianraschka](https:\u002F\u002Fsebastianraschka.com\u002Fblog\u002F2021\u002Fdl-course.html)\n | Deep Learning **NYU**\t\t\t\t\t \t\t\t\t\t| [WebSite](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F)  [2021](https:\u002F\u002Fatcold.github.io\u002FNYU-DLSP21\u002F) |\n | Deep Learning (CS182) **UC Berkeley**\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A)\n | Deep Learning Lecture Series\t**DeepMind x UCL**\t\t\t    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF)|\n | Deep Learning (CS230) **Stanford**\t\t\t\t\t\t    | [WebSite](https:\u002F\u002Fcs230.stanford.edu\u002Flecture\u002F)               | \n | CNN for Visual Recognition(CS231n) **Stanford**    \t\t    | [WebSite-2020](https:\u002F\u002Fcs231n.github.io\u002F)  [YouTube-2017](https:\u002F\u002Ftinyurl.com\u002Fy2gghbvs)|\n | Full Stack Deep Learning   \t\t\t\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fcourse.fullstackdeeplearning.com\u002F)[2021](https:\u002F\u002Ffullstackdeeplearning.com\u002Fspring2021\u002F)|\n | Practical Deep Learning for Coders, v3                       | [fast.ai](https:\u002F\u002Fcourse19.fast.ai\u002Findex.html)\t\t\t   |\n | Deep Learning Crash Course 2021 d2l.ai \t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZSO_6-bSqHQsDaBNtcFwMQuJw_djFnbd)|\n | Deep Learning for Computer Vision **Michigan**\t\t\t\t| [WebSite](https:\u002F\u002Fweb.eecs.umich.edu\u002F~justincj\u002Fteaching\u002Feecs498\u002FFA2020\u002F)|\n | Neural Networks from Scratch in Python by Sentdex\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?app=desktop&list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3)|\n | Keras - Python Deep Learning Neural Network API\t\t\t\t| [deeplizard](https:\u002F\u002Fdeeplizard.com\u002Flearn\u002Fvideo\u002FRznKVRTFkBY)|\n | Reproducible Deep Learning\t\t\t\t\t\t\t\t\t| [sscardapane.it](https:\u002F\u002Fwww.sscardapane.it\u002Fteaching\u002Freproducibledl\u002F)|\n | PyTorch Fundamentals \t\t\t\t\t\t\t\t\t\t| [microsoft](https:\u002F\u002Fdocs.microsoft.com\u002Fen-us\u002Flearn\u002Fpaths\u002Fpytorch-fundamentals\u002F)|\n | Geometric Deep Learing (GDL100)\t\t\t\t\t\t\t\t| [geometricdeeplearning](https:\u002F\u002Fgeometricdeeplearning.com\u002Flectures\u002F)|\n | Deep learning Neuromatch Academy \t\t\t\t\t\t\t| [neuromatch](https:\u002F\u002Fdeeplearning.neuromatch.io\u002Ftutorials\u002Fintro.html)\n | Deep Learning for Molecules and Materials\t\t\t\t\t| [WebSite](https:\u002F\u002Fwhitead.github.io\u002Fdmol-book\u002Fintro.html)|\n | Deep Learning course for Vision\t\t\t\t\t\t\t\t| [arthurdouillard.com](https:\u002F\u002Farthurdouillard.com\u002Fdeepcourse\u002F)|\n | Deep Multi-Task and Meta Learning (CS330) **Stanford**  \t\t| [WebSite](https:\u002F\u002Fcs330.stanford.edu\u002F) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5)|\n | Deep Learning Interviews book \t\t\t\t\t\t\t\t| [WebSite](https:\u002F\u002Fgithub.com\u002FBoltzmannEntropy\u002Finterviews.ai)|\n | Deep Learning for Computer Vision 2021                       | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_Z2_U9MIJdNgFM7-f2fZ9ZxjVRP_jhJv)\n | Deep Learning 2022 **CMU**                                   | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLp-0K3kfddPxRmjgjm0P1WT6H-gTqE8j9)   \n | UvA Deep Learning                                            | [WebSite](https:\u002F\u002Fuvadlc.github.io\u002F)\n\n\n## Natural language processing \n\n | Title and Source                                             | Link                               \t\t\t\t  \t\t   |\n | ------------------------------------------------------------ | -----------------------------------------------------------|\n | Natural Language Processing AWS\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8P_Z6C4GcuWfAq8Pt6PBYlck4OprHXsw)\n | NLP - Krish Naik \t\t\t\t                            | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZoTAELRMXVMdJ5sqbCK2LiM0HhQVWNzm)\n | NLP with Deep Learning(CS224N) 2019 **Stanford**     \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z) [2021](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ)\n | A Code-First Introduction to Natural Language Processing     | [fast.ai](https:\u002F\u002Fwww.fast.ai\u002F2019\u002F07\u002F08\u002Ffastai-nlp\u002F)|\n | CMU Neural Nets for NLP 2021  **Carnegie Mellon University** | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8AkaHEJ7lOOrlex-pcxS-XV)|\n | Speech and Language Processing **Stanford** \t\t\t\t\t| [WebSite](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) |\n | Natural Language Understanding (CS224U) **Stanford**\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rObpMCir6rNNUlFAn56Js20) [2022](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224u\u002F)\n | NLP with Dan Jurafsky and Chris Manning, 2012 **Stanford**   | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOFZnDyrlW3-nI7tMLtmiJZ)|\n | Intro to NLP with spaCy   \t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLBmcuObd5An559HbDr_alBnwVsGq-7uTF)|\n | Advanced NLP with spaCy \t\t\t\t\t\t\t\t\t\t| [website](https:\u002F\u002Fcourse.spacy.io\u002Fen\u002F)                                             |\n | Applied Language Technology \t\t\t\t\t\t\t\t\t| [website](https:\u002F\u002Fapplied-language-technology.readthedocs.io\u002Fen\u002Flatest\u002F)|\n | Advanced Natural Language Processing **Umass**\t\t\t\t| [website](https:\u002F\u002Fpeople.cs.umass.edu\u002F~miyyer\u002Fcs685\u002Fschedule.html) [YouTube 2020](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLWnsVgP6CzadmQX6qevbar3_vDBioWHJL)|\n | Huggingface Course\t\t\t\t\t\t\t\t\t\t\t| [huggingface.co](https:\u002F\u002Fhuggingface.co\u002Fcourse\u002Fchapter1?fw=tf)|\n | NLP Course **Michigan**\t\t\t\t\t\t\t\t\t\t| [github](https:\u002F\u002Fgithub.com\u002Fdeskool\u002Fnlp-class)|\n | Multilingual NLP 2020 **CMU**\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8CHhppU6n1Q9-04m96D9gt5)|\n | Advanced NLP 2021 **CMU**\t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8AYSXn_GKVgwXVluCT9chJ6)|\n | Transformers United **stanford**                             | [Website](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F)  [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM) |  \n | CS324 Large Language Models | [Website](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2022\u002F)|\n\n  \n\n## Reinforcement learning\n\n | Title and Source                                             | Link\t\t\t\t\t\t\t\t\t\t\t\t\t\t                                         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | Reinforcement Learning(CS234)  **Stanford** \t\t\t\t\t| [YouTube-2019](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u)|\n | Introduction to reinforcement learning **DeepMind**\t\t\t| [YouTube-2015](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ)|\n | Reinforcement Learning Course  **DeepMind & UCL**\t\t\t| [YouTube-2018](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZBKeNJ-JE_eyJHZ7XgBoAyb)|\n | Advanced Deep Learning & Reinforcement Learning        \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDNJre23vqCGIVpfZ_K2RZs)|\n | DeepMind x UCL Reinforcement Learning 2021\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDVH599EItlEWsUOsJbAodm)\n\n\n\n## Large Language Model\n\n| Title and Source                                             | Link |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n| Large Language Model Systems | [Website](https:\u002F\u002Fllmsystem.github.io\u002Fllmsystem2025spring\u002F) |\n| CS336: Language Modeling from Scratch | [Website](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOY23Y0BoGoBGgQ1zmU_MT_)|\n| CME 295: Transformers & Large Language Models | [Website](https:\u002F\u002Fcme295.stanford.edu\u002Fsyllabus\u002F) \n| An Open Course on LLMs, Led by Practitioners |[Website](https:\u002F\u002Fhamel.dev\u002Fblog\u002Fposts\u002Fcourse\u002F)\n\n\n \n## Books\n\n\n | Title and Source                                             | Link                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | Scientific Python Lectures\t\t \t\t\t\t\t\t\t| [ScipyLectures](https:\u002F\u002Fscipy-lectures.org\u002F_downloads\u002FScipyLectures-simple.pdf)|\n | Mathematics for Machine Learning\t\t\t\t\t\t\t    | [mml-book](https:\u002F\u002Fmml-book.github.io\u002Fbook\u002Fmml-book.pdf)\t |\n | An Introduction to Statistical Learning                      | [statlearning](https:\u002F\u002Fwww.statlearning.com\u002F)              |\n | Think Stats \t\t\t\t\t\t\t\t\t\t\t\t\t| [Think Stats](https:\u002F\u002Fgreenteapress.com\u002Fwp\u002Fthink-stats-2e\u002F)|\n | Python Data Science Handbook                                 | [Python For DS](https:\u002F\u002Fjakevdp.github.io\u002FPythonDataScienceHandbook\u002F)|\n | Natural Language Processing with Python - NLTK               | [NLTK](https:\u002F\u002Fwww.nltk.org\u002Fbook\u002F)\t\t\t\t\t\t |\n | Deep Learning by Ian Goodfellow             \t\t\t\t\t| [deeplearningbook](https:\u002F\u002Fwww.deeplearningbook.org\u002F)\t\t |\n | Dive into Deep Learning \t\t\t\t\t\t\t\t\t\t| [d2l.ai](https:\u002F\u002Fd2l.ai\u002Findex.html)\n | Approaching (Almost) Any Machine Learning Problem    \t\t| [AAANLP](https:\u002F\u002Fgithub.com\u002Fabhishekkrthakur\u002Fapproachingalmost\u002Fblob\u002Fmaster\u002FAAAMLP.pdf)|\n | Neural networks and Deep learning\t\t\t\t\t\t\t| [neuralnetworksanddeeplearning](http:\u002F\u002Fneuralnetworksanddeeplearning.com\u002Findex.html)|\n | AutoML: Methods, Systems, Challenges (first book on AutoML)  | [automl](https:\u002F\u002Fwww.automl.org\u002Fbook\u002F)|\n | Feature Engineering and Selection\t \t\t\t\t\t\t| [bookdown.org](https:\u002F\u002Fbookdown.org\u002Fmax\u002FFES\u002F)|\n | Introduction to Machine Learning Interviews Book\t\t\t\t| [huyenchip.com](https:\u002F\u002Fhuyenchip.com\u002Fml-interviews-book\u002F)|\n | Hands-On Machine Learning with R \t\t\t\t\t\t\t| [website](https:\u002F\u002Fbradleyboehmke.github.io\u002FHOML\u002F)|\n | Zero to Mastery TensorFlow for Deep Learning Book\t\t\t| [dev.mrdbourke.com\u002F](https:\u002F\u002Fdev.mrdbourke.com\u002Ftensorflow-deep-learning\u002F)|\n | Introduction to Probability for Data Science\t\t\t\t\t| [probability4datascience](https:\u002F\u002Fprobability4datascience.com\u002F)|\n | Graph Representation Learning Book\t\t\t\t\t\t\t| [cs.mcgill.ca](https:\u002F\u002Fwww.cs.mcgill.ca\u002F~wlh\u002Fgrl_book\u002F)|\n | Interpretable Machine Learning\t\t\t\t\t\t\t\t| [christophm](https:\u002F\u002Fchristophm.github.io\u002Finterpretable-ml-book\u002F)|\n | Computer Vision: Algorithms and Applications, 2nd ed.\t\t| [szeliski.org](https:\u002F\u002Fszeliski.org\u002FBook\u002F)\n\n \n \n \n## ML in Production\n\n\n | Title and Source                                             | Link                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | \tIntroduction to Docker       \t \t\t\t\t\t\t\t| [Docker](https:\u002F\u002Fcarpentries-incubator.github.io\u002Fdocker-introduction\u002F)|\n |  MLOps Basics\t\t\t\t\t\t\t\t\t\t\t\t| [GitHub](https:\u002F\u002Fgithub.com\u002Fgraviraja\u002FMLOps-Basics)| \n |  Effective MLOps: Model Development                           | [wandb](https:\u002F\u002Fwww.wandb.courses\u002Fcourses\u002Feffective-mlops-model-development\u002F)|\n  \n\n## Quantum ML\n\n | Title and Source                                             | Link                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | \tQuantum machine learning      \t \t\t\t\t\t\t\t| [pennylane.ai](https:\u002F\u002Fpennylane.ai\u002Fqml\u002F)|\n\n\n## DataSets\n\n | Title and Source                                             | Link                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | Yelp Open Dataset\t\t\t\t\t\t\t\t\t\t\t| [yelp](https:\u002F\u002Fwww.yelp.com\u002Fdataset)\t\t\t\t\t\t | \n | Machine Translation \t\t\t\t\t\t\t\t\t\t\t| [website](https:\u002F\u002Fwww.manythings.org\u002Fanki\u002F)\t\t\t\t |\n | IndicNLP Corpora (Indian languages)\t\t\t\t\t\t\t| [ai4bharat](https:\u002F\u002Findicnlp.ai4bharat.org\u002Fexplorer\u002F)\t\t |\n | Amazon product co-purchasing network metadata\t\t\t\t| [snap.stanford.edu\u002F](https:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Famazon-meta.html)|\n | Stanford Question Answering Dataset (SQuAD)\t\t\t\t\t| [website](https:\u002F\u002Frajpurkar.github.io\u002FSQuAD-explorer\u002F)\n  \n \n## Other Useful Websites\n\n\n1.\t[Papers with Code](https:\u002F\u002Fpaperswithcode.com\u002Fsota)\n2.\t[Two Minute Papers - Youtube](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FK%C3%A1rolyZsolnai\u002Fvideos)\n3.  [The Missing Semester of Your CS Education](https:\u002F\u002Fmissing.csail.mit.edu\u002F2020\u002F)\n4.  [Workera :  Measure data-AI skills](https:\u002F\u002Fworkera.ai\u002F)\n5.  [Machine learning mastery](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F)\n6.  [From Data to viz: Guide for your graph](https:\u002F\u002Fwww.data-to-viz.com\u002F)\n7.  [datatalks club](https:\u002F\u002Fdatatalks.club\u002F)\n8.  [Machine Learning for Art](https:\u002F\u002Fml4a.net\u002Ffundamentals\u002F)\n10. [applyingml](https:\u002F\u002Fapplyingml.com\u002F)\n11. [Deep Learning Drizzle](https:\u002F\u002Fdeep-learning-drizzle.github.io\u002Findex.html#opt4ml)\n12. [The Machine & Deep Learning Compendium](https:\u002F\u002Fbook.mlcompendium.com\u002F)\n13. [connectedpapers - Research Papers](https:\u002F\u002Fwww.connectedpapers.com\u002F)\n14. [Papers and Latest Research - deepai](https:\u002F\u002Fdeepai.org\u002F)\n15. [Tracking Progress in NLP](https:\u002F\u002Fnlpprogress.com\u002F)\n16. [NLP Blogs by Sebastian Ruder](https:\u002F\u002Fwww.ruder.io\u002F)\n17. [labmlai for papers](https:\u002F\u002Fpapers.labml.ai\u002F)\n\n## Other Useful GitRepo\n\n1. [Applied-ml - Papers and blogs by organizations ](https:\u002F\u002Fgithub.com\u002Feugeneyan\u002Fapplied-ml)\n2. [List Machine learning Python libraries](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n3. [ML From Scratch - Implementations of models\u002Falgorithms](https:\u002F\u002Fgithub.com\u002Feriklindernoren\u002FML-From-Scratch)\n4. [What the f*ck Python?](https:\u002F\u002Fgithub.com\u002Fsatwikkansal\u002Fwtfpython)\n5. [scikit-learn user guide: step-step approach](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002Fuser_guide.html)\n6. [NLP Tutorial Code with DL](https:\u002F\u002Fgithub.com\u002Fgraykode\u002Fnlp-tutorial)\n7. [awesome-mlops](https:\u002F\u002Fgithub.com\u002Fvisenger\u002Fawesome-mlops)\n8. [Text Classification Algorithms: A Survey](https:\u002F\u002Fgithub.com\u002Fkk7nc\u002FText_Classification)\n9. [ML use cases by company](https:\u002F\u002Fgithub.com\u002Fkhangich\u002Fmachine-learning-interview\u002Fblob\u002Fmaster\u002Fappliedml.md)\n\n## Blogs and Webinar\n1. [Recommendation algorithms and System design](https:\u002F\u002Fwww.theinsaneapp.com\u002F2021\u002F03\u002Fsystem-design-and-recommendation-algorithms.html)\n2. [Machine Learning System Design](https:\u002F\u002Fbecominghuman.ai\u002Fmachine-learning-system-design-f2f4018f2f8?gi=942874b21d0e)\n\n\n## Must Read Research Paper & WebBooks\n\n **NLP [Text]** \n\n1. [Text Classification Algorithms: A Survey](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.08067)\n2. [Deep Learning Based Text Classification: A Comprehensive Review](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.03705)\n3. [Compression of Deep Learning Models for Text: A Survey](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.05221)\n4. [A Survey on Text Classification: From Shallow to Deep Learning](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.00364.pdf)\n4. [A Survey of Transformers](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04554)\n5. [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.05542)\n6. [Graph Neural Networks for Natural Language Processing: A Survey](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06090)\n8. [A Survey of Data Augmentation Approaches for NLP](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.03075)\n9. [A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.201.pdf)\n10. [Evaluation of Text Generation: A Survey](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.14799.pdf) \n11. [A Survey of Transfer learning In NLP](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.04239.pdf)\n12. [A Systematic Survey of Prompting Methods in NLP](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.13586.pdf)\n\n**OCR [Optical Character Recognition]** \n\n1. [Survey of Post-OCR Processing Approaches](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3453476)\n\n**LLM (Large Language Models)**\n\n1. [Foundations of Large Language Models](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2501.09223)\n2. [On the Biology of a Large Language Model : Anthropic](https:\u002F\u002Ftransformer-circuits.pub\u002F2025\u002Fattribution-graphs\u002Fbiology.html)\n3. [Vision-Language Models](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2404.07214)\n4. [LLM Inference Handbook](https:\u002F\u002Fbentoml.com\u002Fllm\u002F)\n5. [Inside vLLM: LLM Inference System](https:\u002F\u002Fwww.aleksagordic.com\u002Fblog\u002Fvllm)\n6. [MCP : Model Context Protocol](https:\u002F\u002Fmodelcontextprotocol.io\u002Fdocs\u002Fgetting-started\u002Fintro)\n7. [In-Context Learning](https:\u002F\u002Fintro-to-icl.github.io\u002F)\n\n\n\n## Tech Blogs \n\n**Company**\n\n1. [AssemblyAI](https:\u002F\u002Fwww.assemblyai.com\u002Fblog)\n2. [Grammarly](https:\u002F\u002Fwww.grammarly.com\u002Fblog\u002Fengineering\u002F)\n3. [Huggingface](https:\u002F\u002Fhuggingface.co\u002Fblog)\n4. [Uber](https:\u002F\u002Feng.uber.com\u002Fcategory\u002Farticles\u002Fai\u002F)\n5. [Netflix](https:\u002F\u002Fnetflixtechblog.com\u002F)\n6. [Spotify Research](https:\u002F\u002Fresearch.atspotify.com\u002Fblog\u002F) | [Engineering](https:\u002F\u002Fengineering.atspotify.com\u002F)\n7. [Unsloth Blog](https:\u002F\u002Funsloth.ai\u002Fblog)\n8. [Thinking Machines](https:\u002F\u002Fthinkingmachines.ai\u002Fblog\u002F)\n\n**Researcher and Engineers**\n\n0. [TRANSFORMER EXPLAINER](https:\u002F\u002Fpoloclub.github.io\u002Ftransformer-explainer\u002F)\n1. [lilianweng](https:\u002F\u002Flilianweng.github.io\u002F)\n2. [Interconnects](https:\u002F\u002Fwww.interconnects.ai\u002F)\n3. [Ahead of AI by Sebastian Raschka](https:\u002F\u002Fmagazine.sebastianraschka.com\u002F)\n4. [AI by Hand](https:\u002F\u002Fwww.byhand.ai\u002F)\n5. [Lil'BLog](https:\u002F\u002Flilianweng.github.io\u002Flil-log\u002F)\n\n##  Practice Machine Learning\n\n1. [deep-ml](https:\u002F\u002Fwww.deep-ml.com\u002F)\n2. [tensortonic](https:\u002F\u002Fwww.tensortonic.com\u002F)\n3. [tensorgym](https:\u002F\u002Ftensorgym.com\u002F)\n4. [leetgpu](https:\u002F\u002Fleetgpu.com\u002Fchallenges)\n\n\n\n","\u003Cp align=\"center\">\n    \u003Cbr>\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fd0r1h_ML-University_readme_98fd49d3dd3f.png\" width=\"300\"\u002F>\n    \u003Cbr>\n\u003Cp>\n\n\u003Cp align=\"center\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fd0r1h_ML-University_readme_f972e089748d.png\">\n\u003Ca href=\"https:\u002F\u002Ftwitter.com\u002Fintent\u002Ftweet?text=Checkout this awesome Machine Learning University Repo on Github text:&url=https%3A%2F%2Fgithub.com%2Fd0r1h%2FML-University\">\u003Cimg alt=\"tweet\" src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl?style=social&url=https%3A%2F%2Fgithub.com%2Fd0r1h%2FML-University\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">\n    \u003Cp>一所免费的机器学习大学\u003C\u002Fp>\n\u003C\u002Fh3>\n\u003Cbr>\n\n机器学习开源大学是由一位机器学习爱好者发起的，旨在为所有机器学习爱好者提供免费学习资源的创意。\n\n**本列表将持续更新**——如果你是一名机器学习从业者，并且有改进此项目的建议或优质资源想要分享，请提交拉取请求并贡献你的力量。\n\n\n**目录**\n\n1. [入门](#getting-started)\n2. [数学](#mathematics)\n3. [机器学习](#machine-learning)\n4. [深度学习](#deep-learning)\n5. [自然语言处理](#natural-language-processing)\n6. [强化学习](#reinforcement-learning)\n7. [大语言模型](#large-language-model)\n8. [书籍](#books)\n9. [生产环境中的机器学习](#ml-in-production)\n10. [量子机器学习](#quantum-ml)\n11. [数据集](#datasets)\n12. [其他实用网站](#other-useful-websites)\n13. [其他有用的代码库](#other-useful-gitrepo)\n14. [博客和网络研讨会](#blogs-and-webinar) \n15. [必读研究论文](#must-read-research-paper)\n16. [公司技术博客](#company-tech-blogs)\n17. [实践机器学习](#practice-machine-learning)\n\n\n\n\n\n\n\n\n\n## 入门\n\n | 标题与来源                                             | 链接                               \t\t\t\t          |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | AI基础：第一部分                                     | [官网](https:\u002F\u002Fcourse.elementsofai.com\u002F)\t\t\t\t  |\n | AI基础：第二部分                                     | [官网](https:\u002F\u002Fbuildingai.elementsofai.com\u002F) \t\t\t  |\n | 哈佛CS50人工智能导论\t\t\t            | [CS50官网](https:\u002F\u002Fcs50.harvard.edu\u002Fai\u002F2020\u002F)\t\t\t  |\n | MIT计算思维与数据科学导论     | [官网](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-0002-introduction-to-computational-thinking-and-data-science-fall-2016\u002F)\n | 实用数据伦理\t\t\t\t\t\t\t\t\t\t| [fast.ai](https:\u002F\u002Fethics.fast.ai\u002F)\n | 机器学习精通入门 \t\t\t\t\t| [machinelearningmastery](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F)\n | MIT算法设计与分析\t\t\t\t\t| [ocw.mit.edu](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Felectrical-engineering-and-computer-science\u002F6-046j-design-and-analysis-of-algorithms-spring-2015\u002F)\n | 斯坦福AI：原理与技术 \t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rO1NB9TD4iUZ3qghGEGtqNX)|\n | 私人AI系列 \t\t\t\t\t\t\t\t\t\t| [openmined](https:\u002F\u002Fcourses.openmined.org\u002Fcourses)|\n\n \n\n## 数学\n\n\n | 标题与来源                                             | 链接                               \t\t\t\t          |\n |------------------------------------------------------------  | -------------------------------------------------------------\n | 机器学习中的统计学（Krish Naik）                  | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZoTAELRMXVMhVyr3Ri9IQ-t5QPBtxzJO)\n | 针对程序员的计算线性代数\t\t\t\t\t\t| [fast.ai](https:\u002F\u002Fgithub.com\u002Ffastai\u002Fnumerical-linear-algebra\u002Fblob\u002Fmaster\u002FREADME.md)\n | MIT线性代数\t\t\t\t\t\t\t\t\t\t| [官网](https:\u002F\u002Fopenlearninglibrary.mit.edu\u002Fcourses\u002Fcourse-v1:OCW+18.06SC+2T2019\u002Fcourse\u002F)|\n | Zstatistics的统计学\t\t\t\t\t\t\t\t\t| [官网](https:\u002F\u002Fwww.zstatistics.com\u002Fvideos)|\n | 3Blue1Brown的线性代数精髓\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZHQObOWTQDPD3MizzM2xVFitgF8hE_ab)|\n | 看见理论（概率可视化） **布朗大学**    \t\t    | [官网](https:\u002F\u002Fseeing-theory.brown.edu\u002Fbasic-probability\u002Findex.html)|\n | MIT数据分析与机器学习中的矩阵方法 | [官网](https:\u002F\u002Focw.mit.edu\u002Fcourses\u002Fmathematics\u002F18-065-matrix-methods-in-data-analysis-signal-processing-and-machine-learning-spring-2018\u002F)\n | 机器学习数学 \t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?app=desktop&list=PLD80i8An1OEGZ2tYimemzwC3xqkU0jKUg) |\n | MIT应用统计学 | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP60uVBMaoNERc6knT_MgPKS0) \n | 数学思维导论 | [官网](http:\u002F\u002Fimt-decal.org\u002F)|\n\n## 机器学习\n\n | 标题与来源                                             | 链接                               \t\t\t\t           |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | 使用 scikit-learn 的机器学习入门 \t\t\t| [dataschool](https:\u002F\u002Fcourses.dataschool.io\u002Fintroduction-to-machine-learning-with-scikit-learn)|\n | 机器学习导论\t\t\t\t\t\t\t\t| [sebastianraschka](https:\u002F\u002Fsebastianraschka.com\u002Fblog\u002F2021\u002Fml-course.html)\n | 开放式机器学习课程 \t\t\t\t\t\t\t\t| [mlcourse.ai](https:\u002F\u002Fmlcourse.ai\u002F)\t\t\t\t\t\t   |\n | 机器学习（CS229）**斯坦福大学**\t\t\t\t\t\t| [官网](http:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus-spring2020.html) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU)|\n | 机器学习导论 **麻省理工学院** \t\t\t\t\t| [官网](https:\u002F\u002Ftinyurl.com\u002Fybl6udcr)\t\t\t\t\t   |\n | 2021 年机器学习系统设计（CS329S）**斯坦福大学**   | [官网](https:\u002F\u002Fstanford-cs329s.github.io\u002Fsyllabus.html)   |\n | 2020 年应用机器学习（CS5787）**康奈尔理工学院**      | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83)\n | 面向医疗保健的机器学习 **麻省理工学院** \t\t\t\t\t\t| [官网](https:\u002F\u002Ftinyurl.com\u002Fyxgeesdf)\t\t\t\t\t   |\n | 面向交易的机器学习 **佐治亚理工学院**\t\t\t\t| [官网](https:\u002F\u002Flucylabs.gatech.edu\u002Fml4t\u002F)\t\t\t\t   |\t\n | 针对程序员的机器学习导论\t\t\t\t\t| [fast.ai](https:\u002F\u002Fcourse18.fast.ai\u002Fml.html)\n | 机器学习速成课程\t\t\t\t\t\t\t\t| [Google AI](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course)|\n | 使用 Python 的机器学习 \t\t\t\t\t\t\t\t| [freecodecamp](https:\u002F\u002Fwww.freecodecamp.org\u002Flearn\u002Fmachine-learning-with-python\u002F)|\n | 深度强化学习：CS285 **加州大学伯克利分校**\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_iWQOsE6TfURIIhCrlt-wj9ByIVpbfGc)|\n | 概率机器学习 **蒂宾根大学**    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL05umP7R6ij1tHaOFY96m5uX3J21a6yNd)|\n | 使用图的机器学习（CS224W）**斯坦福大学** \t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rPLKxIpqhjhPgdQy7imNkDn)|\n | 生产环境中的机器学习 **卡内基梅隆大学**\t\t\t\t\t\t| [官网](https:\u002F\u002Fckaestne.github.io\u002Fseai\u002F)|\n | 机器学习与深度学习基础                | [deeplizard](https:\u002F\u002Fdeeplizard.com\u002Flearn\u002Fvideo\u002FgZmobeGL0Yg)|\n | 机器学习中的可解释性与透明性      | [官网](https:\u002F\u002Finterpretable-ml-class.github.io\u002F)|\n | 2021 年斯坦福大学实用机器学习\t\t\t\t\t| [官网](https:\u002F\u002Fc.d2l.ai\u002Fstanford-cs329p\u002Findex.html#)|\n | 机器学习 **VU 大学** \t\t\t\t\t\t\t| [官网](https:\u002F\u002Fmlvu.github.io\u002F)|\n | 面向网络安全的机器学习 **普渡大学**    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL74sw1ohGx7GHqDHCkXZeqMQBVUTMrVLE)|\n | 面向机器学习的音频信号处理 \t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL-wATfeyAMNqIee7cH3q1bh4QJFAaeNv0)|\n | 机器学习与因果推断 **斯坦福大学**\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLxq_lXOUlvQAoWZEqhRqHNezS30lI49G-)|\n | 机器学习 cs156 **加州理工学院**                           | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLD63A284B7615313A) |\n | 多模态机器学习（MMML）**卡内基梅隆大学**                   | [官网](https:\u002F\u002Fcmu-multicomp-lab.github.io\u002Fmmml-course\u002Ffall2020\u002F)  [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL-Fhd_vrvisNup9YQs_TdLW7DQz-lda0G) | \n | 加州理工学院高级机器学习专题              | [官网](https:\u002F\u002F1five9.github.io\u002F)\n\n## 深度学习\n \n \n | 标题与来源                                             | 链接                               \t\t\t\t           |\n |------------------------------------------------------------  | -------------------------------------------------------------|\n | 深度学习导论(6.S191) **MIT**\t\t \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI)\t\t\t\t\t   |\n | 深度学习导论\t\t\t\t\t\t\t\t| [sebastianraschka](https:\u002F\u002Fsebastianraschka.com\u002Fblog\u002F2021\u002Fdl-course.html)\n | 深度学习 **NYU**\t\t\t\t\t \t\t\t\t\t| [Website](https:\u002F\u002Fatcold.github.io\u002Fpytorch-Deep-Learning\u002F)  [2021](https:\u002F\u002Fatcold.github.io\u002FNYU-DLSP21\u002F) |\n | 深度学习 (CS182) **UC Berkeley**\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_iWQOsE6TfVmKkQHucjPAoRtIJYt8a5A)\n | 深度学习讲座系列 **DeepMind x UCL**\t\t\t    | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZCDxZ44o4p3N5Anz3lLRVZF)|\n | 深度学习 (CS230) **Stanford**\t\t\t\t\t\t    | [Website](https:\u002F\u002Fcs230.stanford.edu\u002Flecture\u002F)               | \n | 用于视觉识别的卷积神经网络(CS231n) **Stanford**    \t\t    | [Website-2020](https:\u002F\u002Fcs231n.github.io\u002F)  [YouTube-2017](https:\u002F\u002Ftinyurl.com\u002Fy2gghbvs)|\n | 全栈深度学习   \t\t\t\t\t\t\t\t\t| [Website](https:\u002F\u002Fcourse.fullstackdeeplearning.com\u002F)[2021](https:\u002F\u002Ffullstackdeeplearning.com\u002Fspring2021\u002F)|\n | 针对编码者的实用深度学习，v3                       | [fast.ai](https:\u002F\u002Fcourse19.fast.ai\u002Findex.html)\t\t\t   |\n | 2021年深度学习速成课 d2l.ai \t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_Z2_U9MIJdNgFM7-f2fZ9ZxjVRP_jhJv)|\n | 密歇根大学计算机视觉领域的深度学习\t\t\t\t| [Website](https:\u002F\u002Fweb.eecs.umich.edu\u002F~justincj\u002Fteaching\u002Feecs498\u002FFA2020\u002F)|\n | Sentdex用Python从头开始构建神经网络\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?app=desktop&list=PLQVvvaa0QuDcjD5BAw2DxE6OF2tius3V3)|\n | Keras - Python深度学习神经网络API\t\t\t\t| [deeplizard](https:\u002F\u002Fdeeplizard.com\u002Flearn\u002Fvideo\u002FRznKVRTFkBY)|\n | 可复现的深度学习\t\t\t\t\t\t\t\t\t| [sscardapane.it](https:\u002F\u002Fwww.sscardapane.it\u002Fteaching\u002Freproducibledl\u002F)|\n | PyTorch基础 \t\t\t\t\t\t\t\t\t\t| [microsoft](https:\u002F\u002Fdocs.microsoft.com\u002Fen-us\u002Flearn\u002Fpaths\u002Fpytorch-fundamentals\u002F)|\n | 几何深度学习 (GDL100)\t\t\t\t\t\t\t\t| [geometricdeeplearning](https:\u002F\u002Fgeometricdeeplearning.com\u002Flectures\u002F)|\n | Neuromatch学院的深度学习 \t\t\t\t\t\t\t| [neuromatch](https:\u002F\u002Fdeeplearning.neuromatch.io\u002Ftutorials\u002Fintro.html)\n | 面向分子和材料的深度学习\t\t\t\t\t| [Website](https:\u002F\u002Fwhitead.github.io\u002Fdmol-book\u002Fintro.html)|\n | 视觉领域的深度学习课程\t\t\t\t\t\t\t\t| [arthurdouillard.com](https:\u002F\u002Farthurdouillard.com\u002Fdeepcourse\u002F)|\n | 斯坦福大学多任务与元学习深度学习 (CS330)  \t\t| [Website](https:\u002F\u002Fcs330.stanford.edu\u002F) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ)|\n | 深度学习面试题集 \t\t\t\t\t\t\t\t| [Website](https:\u002F\u002Fgithub.com\u002FBoltzmannEntropy\u002Finterviews.ai)|\n | 2021年计算机视觉领域的深度学习                       | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL_Z2_U9MIJdNgFM7-f2fZ9ZxjVRP_jhJv)\n | 2022年CMU深度学习                                   | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLp-0K3kfddPxRmjgjm0P1WT6H-gTqE8j9)   \n | UvA深度学习                                            | [Website](https:\u002F\u002Fuvadlc.github.io\u002F)\n\n\n## 自然语言处理 \n\n | 标题与来源                                             | 链接                               \t\t\t\t  \t\t   |\n | ------------------------------------------------------------ | -----------------------------------------------------------|\n | AWS自然语言处理\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8P_Z6C4GcuWfAq8Pt6PBYlck4OprHXsw)\n | NLP - Krish Naik \t\t\t\t                            | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLZoTAELRMXVMdJ5sqbCK2LiM0HhQVWNzm)\n | 2019年斯坦福大学深度学习NLP(CS224N)     \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOhcuXMZkNm7j3fVwBBY42z) [2021](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOSH4v6133s9LFPRHjEmbmJ)\n | 以代码为导向的自然语言处理入门     | [fast.ai](https:\u002F\u002Fwww.fast.ai\u002F2019\u002F07\u002F08\u002Ffastai-nlp\u002F)|\n | 卡内基梅隆大学2021年NLP神经网络  **卡内基梅隆大学** | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8AkaHEJ7lOOrlex-pcxS-XV)|\n | 斯坦福大学语音与语言处理 \t\t\t\t\t| [Website](https:\u002F\u002Fweb.stanford.edu\u002F~jurafsky\u002Fslp3\u002F) |\n | 斯坦福大学自然语言理解 (CS224U)\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rObpMCir6rNNUlFAn56Js20) [2022](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs224u\u002F)\n | 2012年斯坦福大学Dan Jurafsky和Chris Manning的NLP   | [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOFZnDyrlW3-nI7tMLtmiJZ)|\n | spaCy自然语言处理入门   \t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLBmcuObd5An559HbDr_alBnwVsGq-7uTF)|\n | spaCy高级自然语言处理 \t\t\t\t\t\t\t\t\t\t| [website](https:\u002F\u002Fcourse.spacy.io\u002Fen\u002F)                                             |\n | 应用语言技术 \t\t\t\t\t\t\t\t\t| [website](https:\u002F\u002Fapplied-language-technology.readthedocs.io\u002Fen\u002Flatest\u002F)|\n | 马萨诸塞大学先进自然语言处理\t\t\t\t| [website](https:\u002F\u002Fpeople.cs.umass.edu\u002F~miyyer\u002Fcs685\u002Fschedule.html) [YouTube 2020](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLWnsVgP6CzadmQX6qevbar3_vDBioWHJL)|\n | Huggingface课程\t\t\t\t\t\t\t\t\t\t\t| [huggingface.co](https:\u002F\u002Fhuggingface.co\u002Fcourse\u002Fchapter1?fw=tf)|\n | 密歇根大学NLP课程\t\t\t\t\t\t\t\t\t\t| [github](https:\u002F\u002Fgithub.com\u002Fdeskool\u002Fnlp-class)|\n | CMU 2020年多语言NLP\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8CHhppU6n1Q9-04m96D9gt5)|\n | CMU 2021年高级NLP\t\t\t\t\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL8PYTP1V4I8AYSXn_GKVgwXVluCT9chJ6)|\n | 斯坦福大学“Transformer联合”                             | [Website](https:\u002F\u002Fweb.stanford.edu\u002Fclass\u002Fcs25\u002F)  [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rNiJRchCzutFw5ItR_Z27CM) |  \n | CS324大型语言模型 | [Website](https:\u002F\u002Fstanford-cs324.github.io\u002Fwinter2022\u002F)|\n\n## 强化学习\n\n | 标题与来源                                             | 链接\t\t\t\t\t\t\t\t\t\t\t\t\t\t                                         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | 强化学习（CS234） **斯坦福大学** \t\t\t\t\t| [YouTube-2019](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOSOPzutgyCTapiGlY2Nd8u)|\n | 强化学习导论 **DeepMind**\t\t\t| [YouTube-2015](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDM-OYHWgPebj2MfCFzFObQ)|\n | 强化学习课程  **DeepMind & UCL**\t\t\t| [YouTube-2018](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZBKeNJ-JE_eyJHZ7XgBoAyb)|\n | 高级深度学习与强化学习        \t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDNJre23vqCGIVpfZ_K2RZs)|\n | DeepMind x UCL 强化学习 2021\t\t\t\t\t| [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLqYmG7hTraZDVH599EItlEWsUOsJbAodm)\n\n\n\n## 大型语言模型\n\n| 标题与来源                                             | 链接 |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n| 大型语言模型系统 | [网站](https:\u002F\u002Fllmsystem.github.io\u002Fllmsystem2025spring\u002F) |\n| CS336：从零开始的语言建模 | [网站](https:\u002F\u002Fstanford-cs336.github.io\u002Fspring2025\u002F) [YouTube](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLoROMvodv4rOY23Y0BoGoBGgQ1zmU_MT_)|\n| CME 295：Transformer与大型语言模型 | [网站](https:\u002F\u002Fcme295.stanford.edu\u002Fsyllabus\u002F) \n| 由从业者主导的LLM开放课程 |[网站](https:\u002F\u002Fhamel.dev\u002Fblog\u002Fposts\u002Fcourse\u002F)\n\n\n \n## 书籍\n\n\n | 标题与来源                                             | 链接                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | 科学Python讲义\t\t \t\t\t\t\t\t\t| [ScipyLectures](https:\u002F\u002Fscipy-lectures.org\u002F_downloads\u002FScipyLectures-simple.pdf)|\n | 机器学习数学\t\t\t\t\t\t\t    | [mml-book](https:\u002F\u002Fmml-book.github.io\u002Fbook\u002Fmml-book.pdf)\t |\n | 统计学习导论                      | [statlearning](https:\u002F\u002Fwww.statlearning.com\u002F)              |\n | 思考统计 \t\t\t\t\t\t\t\t\t\t\t\t\t| [Think Stats](https:\u002F\u002Fgreenteapress.com\u002Fwp\u002Fthink-stats-2e\u002F)|\n | Python数据科学手册                                 | [Python For DS](https:\u002F\u002Fjakevdp.github.io\u002FPythonDataScienceHandbook\u002F)|\n | 使用Python进行自然语言处理 - NLTK               | [NLTK](https:\u002F\u002Fwww.nltk.org\u002Fbook\u002F)\t\t\t\t\t\t |\n | 伊恩·古德费洛的深度学习             \t\t\t\t\t| [deeplearningbook](https:\u002F\u002Fwww.deeplearningbook.org\u002F)\t\t |\n | 深入深度学习 \t\t\t\t\t\t\t\t\t\t| [d2l.ai](https:\u002F\u002Fd2l.ai\u002Findex.html)\n | 解决（几乎）任何机器学习问题    \t\t| [AAANLP](https:\u002F\u002Fgithub.com\u002Fabhishekkrthakur\u002Fapproachingalmost\u002Fblob\u002Fmaster\u002FAAAMLP.pdf)|\n | 神经网络与深度学习\t\t\t\t\t\t\t| [neuralnetworksanddeeplearning](http:\u002F\u002Fneuralnetworksanddeeplearning.com\u002Findex.html)|\n | AutoML：方法、系统、挑战（第一本关于AutoML的书）  | [automl](https:\u002F\u002Fwww.automl.org\u002Fbook\u002F)|\n | 特征工程与选择\t \t\t\t\t\t\t| [bookdown.org](https:\u002F\u002Fbookdown.org\u002Fmax\u002FFES\u002F)|\n | 机器学习面试入门书\t\t\t\t| [huyenchip.com](https:\u002F\u002Fhuyenchip.com\u002Fml-interviews-book\u002F)|\n | 使用R动手实践机器学习 \t\t\t\t\t\t\t| [网站](https:\u002F\u002Fbradleyboehmke.github.io\u002FHOML\u002F)|\n | 从零开始掌握TensorFlow深度学习书\t\t\t| [dev.mrdbourke.com\u002F](https:\u002F\u002Fdev.mrdbourke.com\u002Ftensorflow-deep-learning\u002F)|\n | 数据科学概率论导论\t\t\t\t\t| [probability4datascience](https:\u002F\u002Fprobability4datascience.com\u002F)|\n | 图表示学习书籍\t\t\t\t\t\t\t| [cs.mcgill.ca](https:\u002F\u002Fwww.cs.mcgill.ca\u002F~wlh\u002Fgrl_book\u002F)|\n | 可解释的机器学习\t\t\t\t\t\t\t\t| [christophm](https:\u002F\u002Fchristophm.github.io\u002Finterpretable-ml-book\u002F)|\n | 计算机视觉：算法与应用，第2版\t\t| [szeliski.org](https:\u002F\u002Fszeliski.org\u002FBook\u002F)\n\n \n \n \n## 生产环境中的机器学习\n\n\n | 标题与来源                                             | 链接                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n |  Docker简介       \t \t\t\t\t\t\t\t| [Docker](https:\u002F\u002Fcarpentries-incubator.github.io\u002Fdocker-introduction\u002F)|\n |  MLOps基础                                              | [GitHub](https:\u002F\u002Fgithub.com\u002Fgraviraja\u002FMLOps-Basics)| \n |  有效的MLOps：模型开发                           | [wandb](https:\u002F\u002Fwww.wandb.courses\u002Fcourses\u002Feffective-mlops-model-development\u002F)|\n  \n\n## 量子机器学习\n\n | 标题与来源                                             | 链接                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n |  量子机器学习      \t \t\t\t\t\t\t\t| [pennylane.ai](https:\u002F\u002Fpennylane.ai\u002Fqml\u002F)|\n\n\n## 数据集\n\n | 标题与来源                                             | 链接                               \t\t\t\t         |\n |------------------------------------------------------------  | -----------------------------------------------------------|\n | Yelp开放数据集\t\t\t\t\t\t\t\t\t\t\t| [yelp](https:\u002F\u002Fwww.yelp.com\u002Fdataset)\t\t\t\t\t\t | \n | 机器翻译 \t\t\t\t\t\t\t\t\t\t\t| [网站](https:\u002F\u002Fwww.manythings.org\u002Fanki\u002F)\t\t\t\t |\n | IndicNLP语料库（印度语言）\t\t\t\t\t\t\t| [ai4bharat](https:\u002F\u002Findicnlp.ai4bharat.org\u002Fexplorer\u002F)\t\t |\n | Amazon产品共同购买网络元数据\t\t\t\t| [snap.stanford.edu\u002F](https:\u002F\u002Fsnap.stanford.edu\u002Fdata\u002Famazon-meta.html)|\n | 斯坦福问答数据集（SQuAD）\t\t\t\t\t| [网站](https:\u002F\u002Frajpurkar.github.io\u002FSQuAD-explorer\u002F)\n  \n \n## 其他实用网站\n\n\n1.\t[Papers with Code](https:\u002F\u002Fpaperswithcode.com\u002Fsota)\n2.\t[两分钟论文 - YouTube](https:\u002F\u002Fwww.youtube.com\u002Fc\u002FK%C3%A1rolyZsolnai\u002Fvideos)\n3.  [你计算机科学教育中缺失的一学期](https:\u002F\u002Fmissing.csail.mit.edu\u002F2020\u002F)\n4.  [Workera：衡量数据-AI技能](https:\u002F\u002Fworkera.ai\u002F)\n5.  [机器学习精通](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F)\n6.  [从数据到可视化：你的图表指南](https:\u002F\u002Fwww.data-to-viz.com\u002F)\n7.  [datatalks俱乐部](https:\u002F\u002Fdatatalks.club\u002F)\n8.  [艺术中的机器学习](https:\u002F\u002Fml4a.net\u002Ffundamentals\u002F)\n10. [applyingml](https:\u002F\u002Fapplyingml.com\u002F)\n11. [深度学习细雨](https:\u002F\u002Fdeep-learning-drizzle.github.io\u002Findex.html#opt4ml)\n12. [机器与深度学习汇编](https:\u002F\u002Fbook.mlcompendium.com\u002F)\n13. [connectedpapers - 研究论文](https:\u002F\u002Fwww.connectedpapers.com\u002F)\n14. [论文和最新研究 - deepai](https:\u002F\u002Fdeepai.org\u002F)\n15. [跟踪NLP进展](https:\u002F\u002Fnlpprogress.com\u002F)\n16. [塞巴斯蒂安·鲁德尔的NLP博客](https:\u002F\u002Fwww.ruder.io\u002F)\n17. [labmlai用于论文](https:\u002F\u002Fpapers.labml.ai\u002F)\n\n## 其他有用的 Git 仓库\n\n1. [Applied-ml - 各组织的论文与博客](https:\u002F\u002Fgithub.com\u002Feugeneyan\u002Fapplied-ml)\n2. [机器学习 Python 库列表](https:\u002F\u002Fgithub.com\u002Fml-tooling\u002Fbest-of-ml-python)\n3. [ML From Scratch - 模型\u002F算法实现](https:\u002F\u002Fgithub.com\u002Feriklindernoren\u002FML-From-Scratch)\n4. [What the f*ck Python?](https:\u002F\u002Fgithub.com\u002Fsatwikkansal\u002Fwtfpython)\n5. [scikit-learn 用户指南：循序渐进的方法](https:\u002F\u002Fscikit-learn.org\u002Fstable\u002Fuser_guide.html)\n6. [带有深度学习的 NLP 教程代码](https:\u002F\u002Fgithub.com\u002Fgraykode\u002Fnlp-tutorial)\n7. [awesome-mlops](https:\u002F\u002Fgithub.com\u002Fvisenger\u002Fawesome-mlops)\n8. [文本分类算法：综述](https:\u002F\u002Fgithub.com\u002Fkk7nc\u002FText_Classification)\n9. [公司提供的机器学习用例](https:\u002F\u002Fgithub.com\u002Fkhangich\u002Fmachine-learning-interview\u002Fblob\u002Fmaster\u002Fappliedml.md)\n\n## 博客与网络研讨会\n1. [推荐算法与系统设计](https:\u002F\u002Fwww.theinsaneapp.com\u002F2021\u002F03\u002Fsystem-design-and-recommendation-algorithms.html)\n2. [机器学习系统设计](https:\u002F\u002Fbecominghuman.ai\u002Fmachine-learning-system-design-f2f4018f2f8?gi=942874b21d0e)\n\n\n## 必读的研究论文与网络书籍\n\n**NLP [文本]**\n\n1. [文本分类算法：综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F1904.08067)\n2. [基于深度学习的文本分类：全面综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2004.03705)\n3. [文本深度学习模型压缩：综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2008.05221)\n4. [文本分类综述：从浅层到深度学习](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2008.00364.pdf)\n4. [Transformer 综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.04554)\n5. [AMMUS：自然语言处理中基于 Transformer 的预训练模型综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2108.05542)\n6. [用于自然语言处理的图神经网络：综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2106.06090)\n8. [NLP 数据增强方法综述](https:\u002F\u002Farxiv.org\u002Fabs\u002F2105.03075)\n9. [低资源场景下自然语言处理最新方法综述](https:\u002F\u002Faclanthology.org\u002F2021.naacl-main.201.pdf)\n10. [文本生成评估：综述](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2006.14799.pdf) \n11. [NLP 中迁移学习综述](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2007.04239.pdf)\n12. [NLP 中提示方法的系统性综述](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2107.13586.pdf)\n\n**OCR [光学字符识别]**\n\n1. [OCR 后处理方法综述](https:\u002F\u002Fdl.acm.org\u002Fdoi\u002Fpdf\u002F10.1145\u002F3453476)\n\n**LLM（大型语言模型）**\n\n1. [大型语言模型的基础](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2501.09223)\n2. [大型语言模型的生物学：Anthropic](https:\u002F\u002Ftransformer-circuits.pub\u002F2025\u002Fattribution-graphs\u002Fbiology.html)\n3. [视觉-语言模型](https:\u002F\u002Farxiv.org\u002Fpdf\u002F2404.07214)\n4. [LLM 推理手册](https:\u002F\u002Fbentoml.com\u002Fllm\u002F)\n5. [vLLM 内部：LLM 推理系统](https:\u002F\u002Fwww.aleksagordic.com\u002Fblog\u002Fvllm)\n6. [MCP：模型上下文协议](https:\u002F\u002Fmodelcontextprotocol.io\u002Fdocs\u002Fgetting-started\u002Fintro)\n7. [上下文学习](https:\u002F\u002Fintro-to-icl.github.io\u002F)\n\n\n\n## 技术博客\n\n**公司**\n\n1. [AssemblyAI](https:\u002F\u002Fwww.assemblyai.com\u002Fblog)\n2. [Grammarly](https:\u002F\u002Fwww.grammarly.com\u002Fblog\u002Fengineering\u002F)\n3. [Huggingface](https:\u002F\u002Fhuggingface.co\u002Fblog)\n4. [Uber](https:\u002F\u002Feng.uber.com\u002Fcategory\u002Farticles\u002Fai\u002F)\n5. [Netflix](https:\u002F\u002Fnetflixtechblog.com\u002F)\n6. [Spotify Research](https:\u002F\u002Fresearch.atspotify.com\u002Fblog\u002F) | [Engineering](https:\u002F\u002Fengineering.atspotify.com\u002F)\n7. [Unsloth Blog](https:\u002F\u002Funsloth.ai\u002Fblog)\n8. [Thinking Machines](https:\u002F\u002Fthinkingmachines.ai\u002Fblog\u002F)\n\n**研究者与工程师**\n\n0. [TRANSFORMER EXPLAINER](https:\u002F\u002Fpoloclub.github.io\u002Ftransformer-explainer\u002F)\n1. [lilianweng](https:\u002F\u002Flilianweng.github.io\u002F)\n2. [Interconnects](https:\u002F\u002Fwww.interconnects.ai\u002F)\n3. [Sebastian Raschka 的 Ahead of AI 杂志](https:\u002F\u002Fmagazine.sebastianraschka.com\u002F)\n4. [AI by Hand](https:\u002F\u002Fwww.byhand.ai\u002F)\n5. [Lil'BLog](https:\u002F\u002Flilianweng.github.io\u002Flil-log\u002F)\n\n## 机器学习实践\n\n1. [deep-ml](https:\u002F\u002Fwww.deep-ml.com\u002F)\n2. [tensortonic](https:\u002F\u002Fwww.tensortonic.com\u002F)\n3. [tensorgym](https:\u002F\u002Ftensorgym.com\u002F)\n4. [leetgpu](https:\u002F\u002Fleetgpu.com\u002Fchallenges)","# ML-University 快速上手指南\n\n**注意**：`ML-University` 并非一个需要安装的软件库或框架，而是一个**开源的机器学习学习资源索引仓库**。它汇集了全球顶尖高校（如斯坦福、MIT、哈佛等）和机构的免费课程、书籍、论文及数据集链接。\n\n本指南将指导你如何获取该资源列表，并高效地利用其中的内容开始学习。\n\n## 1. 环境准备\n\n由于本项目本质上是文档和资源链接集合，无需特殊的计算资源或深度学习环境即可浏览。但为了实践资源中的代码示例，建议准备以下基础环境：\n\n*   **操作系统**：Windows, macOS 或 Linux 均可。\n*   **浏览器**：推荐 Chrome 或 Edge，用于访问课程网站和视频。\n*   **编程环境（可选，用于实战）**：\n    *   Python 3.8+\n    *   包管理工具：`pip` 或 `conda`\n    *   常用库：`numpy`, `pandas`, `scikit-learn`, `pytorch` 或 `tensorflow`（具体取决于你选择的课程）。\n*   **Git**：用于克隆本仓库到本地以便离线查阅目录。\n\n## 2. 安装步骤（获取资源列表）\n\n你可以通过以下两种方式获取 `ML-University` 的资源列表：\n\n### 方式一：在线浏览（推荐）\n直接访问 GitHub 仓库页面，利用目录导航查找所需领域的资源：\n> https:\u002F\u002Fgithub.com\u002Fd0r1h\u002FML-University\n\n### 方式二：克隆到本地\n如果你希望离线保存或在本地整理学习计划，可以使用 Git 克隆：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fd0r1h\u002FML-University.git\ncd ML-University\n```\n\n*注：国内用户若遇到克隆速度慢的问题，可使用国内镜像源（如 Gitee 镜像，若有）或配置 Git 代理加速。*\n\n## 3. 基本使用\n\n`ML-University` 的核心用法是根据你的学习阶段和技术兴趣，在 `README.md` 文件中找到对应的章节并点击链接跳转学习。\n\n### 步骤 1：确定学习路径\n打开克隆后的 `README.md` 文件或在线查看目录，主要包含以下核心板块：\n\n*   **Getting Started**: 适合零基础入门（推荐 *Elements of AI* 或 *CS50's Introduction to AI*）。\n*   **Mathematics**: 补充数学基础（线性代数、统计学）。\n*   **Machine Learning**: 经典机器学习算法（推荐 *Stanford CS229* 或 *Andrew Ng 课程*）。\n*   **Deep Learning**: 深度学习进阶（推荐 *MIT 6.S191* 或 *Stanford CS231n*）。\n*   **Natural Language Processing (NLP)**: 自然语言处理专项。\n*   **LLM**: 大语言模型最新资源。\n*   **Practice Machine Learning**: 实战练习平台。\n\n### 步骤 2：选择课程并开始\n假设你想从零开始学习机器学习基础：\n\n1.  定位到 **Getting Started** 章节。\n2.  点击 **Elements of AI : Part-1** 链接。\n3.  跳转至官方网站 `https:\u002F\u002Fcourse.elementsofai.com\u002F` 进行注册和学习。\n\n假设你想深入深度学习并配合代码实战：\n\n1.  定位到 **Deep Learning** 章节。\n2.  选择 **Practical Deep Learning for Coders, v3 (fast.ai)**。\n3.  点击链接进入 `https:\u002F\u002Fcourse19.fast.ai\u002Findex.html`。\n4.  按照该课程指引，在本地终端安装依赖并运行代码（通常涉及如下命令，具体以课程要求为准）：\n\n```bash\n# 示例：安装 fastbook 相关依赖（参考 fast.ai 课程）\npip install fastbook\n```\n\n### 步骤 3：贡献与更新\n该列表持续更新。如果你发现了优质的新资源，可以通过 GitHub 提交 Pull Request (PR) 来丰富这个知识库：\n\n```bash\n# 创建新分支进行修改\ngit checkout -b add-new-resource\n# 编辑 README.md 添加资源链接\n# 提交并推送\ngit commit -m \"Add new resource: [Resource Name]\"\ngit push origin add-new-resource\n```\n\n通过上述步骤，你可以将 `ML-University` 作为你的个人机器学习“大学”课表，系统地规划从数学基础到前沿大模型的学习路线。","刚转行进入 AI 领域的初级算法工程师李明，正试图从零构建系统的机器学习知识体系以应对新项目的技术选型挑战。\n\n### 没有 ML-University 时\n- **资源检索碎片化**：需要在谷歌、GitHub 和各类论坛间反复切换搜索，难以区分教程的深浅与权威性，耗费大量时间在筛选低质内容上。\n- **学习路径缺失**：面对数学基础、深度学习、NLP 等众多分支，不清楚学习的先后顺序，容易陷入“只见树木不见森林”的知识盲区。\n- **前沿技术脱节**：难以快速找到关于大语言模型（LLM）或量子机器学习等最新领域的优质入门资源，导致技术方案滞后。\n- **理论与实践割裂**：找到了理论课程却找不到对应的数据集或生产环境部署指南，导致知识无法落地转化为代码能力。\n\n### 使用 ML-University 后\n- **一站式权威导航**：直接利用 ML-University 整理的分类目录，快速获取来自哈佛、MIT、Stanford 等顶尖高校的结构化课程链接，省去甄别成本。\n- **清晰进阶路线图**：参照其从\"Getting Started\"到\"Mathematics\"再到各垂直领域的目录结构，制定了由浅入深的系统学习计划，避免盲目跳跃。\n- **紧跟技术浪潮**：通过专门的 LLM 和 Quantum ML 章节，迅速定位到最新的研究论文和技术博客，确保技术视野与行业前沿同步。\n- **全链路闭环学习**：依据\"ML in Production\"和\"DataSets\"板块，顺利找到从数据获取到模型部署的完整实战资源，快速将理论应用于项目开发。\n\nML-University 将分散的全球优质教育资源整合为一张清晰的地图，让学习者从“大海捞针”转变为“按图索骥”，极大提升了自我成长的效率与质量。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fd0r1h_ML-University_3c45351c.png","d0r1h","Pawan Trivedi","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fd0r1h_d1d9a61b.png",null,"https:\u002F\u002Fgithub.com\u002Fd0r1h",936,120,"2026-04-08T22:47:19",1,"","未说明",{"notes":26,"python":24,"dependencies":27},"该项目并非一个可执行的软件工具或代码库，而是一个机器学习学习资源的汇总列表（类似课程大纲）。它主要包含指向外部网站、视频课程、书籍和教程的链接，因此不需要安装任何特定的操作系统、GPU、内存、Python 版本或依赖库即可浏览和使用。",[],[29,30,31,32],"开发框架","数据工具","其他","语言模型",[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"machine-learning","open-source","university","artificial-intelligence","learning","awsome","awsome-list","free","deep-learning","natural-language-processing","mathematics","course","computer-science","data-science","reinforcement-learning","neural-network",2,"ready","2026-03-27T02:49:30.150509","2026-04-14T12:27:56.890369",[],[],[57,68,76,84,92,101],{"id":58,"name":59,"github_repo":60,"description_zh":61,"stars":62,"difficulty_score":63,"last_commit_at":64,"category_tags":65,"status":51},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",[66,29,67,30],"Agent","图像",{"id":69,"name":70,"github_repo":71,"description_zh":72,"stars":73,"difficulty_score":63,"last_commit_at":74,"category_tags":75,"status":51},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",[29,67,66],{"id":77,"name":78,"github_repo":79,"description_zh":80,"stars":81,"difficulty_score":50,"last_commit_at":82,"category_tags":83,"status":51},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",154349,"2026-04-13T23:32:16",[29,66,32],{"id":85,"name":86,"github_repo":87,"description_zh":88,"stars":89,"difficulty_score":50,"last_commit_at":90,"category_tags":91,"status":51},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。",108322,"2026-04-10T11:39:34",[29,67,66],{"id":93,"name":94,"github_repo":95,"description_zh":96,"stars":97,"difficulty_score":50,"last_commit_at":98,"category_tags":99,"status":51},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",[100,66,67,29],"插件",{"id":102,"name":103,"github_repo":104,"description_zh":105,"stars":106,"difficulty_score":50,"last_commit_at":107,"category_tags":108,"status":51},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",[100,29]]