[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tool-CodingTrain--Machine-Learning":3,"similar-CodingTrain--Machine-Learning":39},{"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":18,"owner_location":18,"owner_email":18,"owner_twitter":19,"owner_website":20,"owner_url":21,"languages":18,"stars":22,"forks":23,"last_commit_at":24,"license":18,"difficulty_score":25,"env_os":26,"env_gpu":27,"env_ram":27,"env_deps":28,"category_tags":31,"github_topics":18,"view_count":33,"oss_zip_url":18,"oss_zip_packed_at":18,"status":34,"created_at":35,"updated_at":36,"faqs":37,"releases":38},9872,"CodingTrain\u002FMachine-Learning","Machine-Learning","Examples and experiments around ML for upcoming Coding Train videos","Machine-Learning 是由知名编程教育频道 Coding Train 维护的开源项目，旨在为初学者和创意开发者提供机器学习领域的实验案例与学习资源。它主要解决了机器学习入门门槛高、理论枯燥难懂的问题，通过大量可视化的代码示例和精心筛选的文章、书籍及视频链接，将复杂的算法概念转化为直观有趣的实践内容。\n\n该项目特别适合编程初学者、创意设计师、艺术创作者以及对人工智能感兴趣但缺乏数学背景的用户。其独特亮点在于采用了生动的标签系统（如“创意”、“入门”、“进阶”），帮助用户根据自身水平快速定位合适的学习资料；同时，资源涵盖从基础的决策树到深度强化学习等广泛主题，并强调使用 JavaScript、Processing 等易于上手的语言进行实现，鼓励用户在创作中探索技术。无论是想动手写第一个神经网络，还是寻找灵感进行艺术实验，Machine-Learning 都是一个友好且实用的起点。","[![Dreams in the CodingTrain](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FCodingTrain_Machine-Learning_readme_9189a9e7e009.jpg)](http:\u002F\u002Fthecodingtrain.com\u002F)\n\n# Machine-Learning\nExamples and experiments around ML for upcoming Coding Train videos and ITP course.\n\n# Resource attributes\n\nSince resources across the internet vary in terms of their pre-requisites and general accessibility, it is useful to\ngive attributes to them so that it is easy to understand where a resource fits into the wider machine learning scope. Below is a few suggested attributes (please extend):\n\n - :rainbow: = creative\n - :bowtie: = beginner\n - :sweat_smile: = intermediate, some pre-requisites\n - :godmode: = advanced, many pre-requisites\n\n# Table of Contents\n\u003C!-- MarkdownTOC depth=4 -->\n- [Articles & Posts](#articles--posts)\n- [Books](#books)\n- [Courses](#courses)\n- [Examples](#examples)\n- [Projects](#projects)\n- [Videos](#videos)\n- [Resources](#resources)\n- [Newsletter](#newsletter)\n- [Tools](#tools)\n    - [Tensorflow](#tensorflow)\n    - [t-SNE](#t-sne)\n\n\u003C!-- \u002FMarkdownTOC -->\n## Articles & Posts\n  1. [A Return to Machine Learning](https:\u002F\u002Fmedium.com\u002F@kcimc\u002Fa-return-to-machine-learning-2de3728558eb#.vlqnbo9yg) :rainbow: :bowtie:\n  1. [A Visual Introduction to Machine Learning](http:\u002F\u002Fwww.r2d3.us\u002Fvisual-intro-to-machine-learning-part-1\u002F) :rainbow: :bowtie:\n  1. [Machine Learning is Fun!](https:\u002F\u002Fmedium.com\u002F@ageitgey\u002Fmachine-learning-is-fun-80ea3ec3c471) :bowtie:\n  1. [Deep Reinforcement Learning: Pong from Pixels](http:\u002F\u002Fkarpathy.github.io\u002F2016\u002F05\u002F31\u002Frl\u002F) :rainbow:\n  1. [Inside Libratus, the Poker AI That Out-Bluffed the Best Humans](https:\u002F\u002Fwww.wired.com\u002F2017\u002F02\u002Flibratus\u002F?imm_mid=0ed017&cmp=em-data-na-na-newsltr_ai_20170206) :bowtie:\n  1. [Machine Learning in Javascript: Introduction](http:\u002F\u002Fburakkanber.com\u002Fblog\u002Fmachine-learning-in-other-languages-introduction\u002F) :bowtie:\n  1. [Realtime control of sequence generation with character based Long Short Term Memory Recurrent Neural Networks](http:\u002F\u002Fwww.iggi.org.uk\u002Fassets\u002FIGGI-2016-Memo-A.pdf) :sweat_smile:\n  1. [Why is machine learning 'hard'?](http:\u002F\u002Fai.stanford.edu\u002F~zayd\u002Fwhy-is-machine-learning-hard.html) :bowtie:\n  1. [Unreasonable effectiveness of RNNs](http:\u002F\u002Fkarpathy.github.io\u002F2015\u002F05\u002F21\u002Frnn-effectiveness\u002F) :sweat_smile:\n  1. [colah's blog](http:\u002F\u002Fcolah.github.io\u002F)\n  1. ‪[Machine Learning Website with many Tutorial of Machine Learning‪](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F‬) ‬:rainbow:\n  1. [Beginners tutorial for decision tree implementation](https:\u002F\u002Fwww.dezyre.com\u002Fdata-science-in-r-programming-tutorial\u002Fdecision-tree-tutorial) :rainbow:‪\n  1. [Machine Learning Beginner tutorial Supervised and Unsupervised Learning](http:\u002F\u002Fdataaspirant.com\u002F2014\u002F09\u002F19\u002Fsupervised-and-unsupervised-learning\u002F‬) :rainbow:‪\n  1. [Q-Learning Tutorial](http:\u002F\u002Foutlace.com\u002Frlpart3.html) :sweat_smile:\n  1. [Big O notation Free Code Camp](https:\u002F\u002Fmedium.freecodecamp.com\u002Ftime-is-complex-but-priceless-f0abd015063c?source=linkShare-4599aaae9f0b-1489449307) :bowtie:\n  1. [Ray Wenderlich Big O notation](https:\u002F\u002Fgithub.com\u002Fraywenderlich\u002Fswift-algorithm-club\u002Fblob\u002Fmaster\u002FBig-O%20Notation.markdown) :bowtie:\n  1. [Interview Cake Big O notation](https:\u002F\u002Fwww.interviewcake.com\u002Farticle\u002Fjava\u002Fbig-o-notation-time-and-space-complexity) :bowtie:\n  1. [Youtube Video Big O notation Derek Banas](https:\u002F\u002Fm.youtube.com\u002Fwatch?v=V6mKVRU1evU) :bowtie:\n  1. [Youtube Video for Big O notation HackerRank](https:\u002F\u002Fyoutu.be\u002Fv4cd1O4zkGw) :bowtie:\n  1. [Random Forest in Python](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002Frandom-forests-in-python.html) :sweat_smile:\n  1. [CreativeAI - On the Democratisation & Escalation of Creativity](https:\u002F\u002Fmedium.com\u002F@creativeai\u002Fcreativeai-9d4b2346faf3#.8oaibcklb) :rainbow: :bowtie:\n  1. [Reducing the Dimensionality of Data with Neural Networks](https:\u002F\u002Fwww.cs.toronto.edu\u002F~hinton\u002Fscience.pdf)\n  1. [Learning Deep Architectures for AI](https:\u002F\u002Fwww.iro.umontreal.ca\u002F~bengioy\u002Fpapers\u002Fftml.pdf)\n  1. [Let’s code a Neural Network from scratch (Processing)](https:\u002F\u002Fmedium.com\u002Ftypeme\u002Flets-code-a-neural-network-from-scratch-part-1-24f0a30d7d62) :sweat_smile:\n  1. [Distill - Demystifying Machine Learning Research](http:\u002F\u002Fdistill.pub\u002F)\n  1. [Machine Learning in Javascript](http:\u002F\u002Fburakkanber.com\u002Ftag\u002Fml-in-js\u002F) :sweat_smile:\n  1. [A.I. Experiments from google](https:\u002F\u002Faiexperiments.withgoogle.com\u002F)    \n  1. [Rohan & Lenny #3: Recurrent Neural Networks & LSTMs](https:\u002F\u002Fayearofai.com\u002Frohan-lenny-3-recurrent-neural-networks-10300100899b) :sweat_smile:\n  1. [Backpropogating an LSTM: A Numerical Example](https:\u002F\u002Fmedium.com\u002F@aidangomez\u002Flet-s-do-this-f9b699de31d9) :sweat_smile:\n  1. [Naive Bayes for Dummies; A Simple Explanation](http:\u002F\u002Fblog.aylien.com\u002Fnaive-bayes-for-dummies-a-simple-explanation\u002F) :bowtie:\n  1. [Machine Learning Crash Course @ Berkeley](https:\u002F\u002Fml.berkeley.edu\u002Fblog\u002Ftutorials\u002F) :bowtie: :godmode:\n  1. [How to approach almost any ML problem?](http:\u002F\u002Fblog.kaggle.com\u002F2016\u002F07\u002F21\u002Fapproaching-almost-any-machine-learning-problem-abhishek-thakur\u002F) :sweat_smile:\n  1. [Technical Notes on ML & AI by Chris Albon](https:\u002F\u002Fchrisalbon.com\u002F#machine_learning) :bowtie: :sweat_smile:\n  1. [Naive Bayes and Text Classification](https:\u002F\u002Fsebastianraschka.com\u002FArticles\u002F2014_naive_bayes_1.html) :sweat_smile:\n  1. [First Contact With TensorFlow](https:\u002F\u002Ftorres.ai\u002Fresearch-teaching\u002Ftensorflow\u002Ffirst-contact-with-tensorflow-book\u002Ffirst-contact-with-tensorflow\u002F) :sweat_smile:\n\n## Books\n  1. [Machine Learning for Designers](http:\u002F\u002Fwww.oreilly.com\u002Fdesign\u002Ffree\u002Fmachine-learning-for-designers.csp) by [Patrick Hebron](http:\u002F\u002Fwww.patrickhebron.com\u002F), [Accompanying Webcast: Machine learning and the future of design](http:\u002F\u002Fwww.oreilly.com\u002Fpub\u002Fe\u002F3709)\n  1. [Machine Learning Book](https:\u002F\u002Fmachinelearningmastery.com\u002Fmaster-machine-learning-algorithms\u002F) :rainbow:\n  1. [A first encounter with machine learning](https:\u002F\u002Fwww.ics.uci.edu\u002F~welling\u002Fteaching\u002FICS273Afall11\u002FIntroMLBook.pdf) :bowtie:\n  1. [Natural Language Processing with Python](https:\u002F\u002Fwww.nltk.org\u002Fbook\u002F) :sweat_smile: :bowtie:\n  1. [A Brief Introduction to Neural Networks](http:\u002F\u002Fwww.dkriesel.com\u002Fen\u002Fscience\u002Fneural_networks) :sweat_smile:\n\n\n## Courses\n  1. [Machine Learning Crash Course By Google](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course\u002F) :bowtie:\n  2. [Coursera - Machine Learning with TensorFlow on GCP](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-tensorflow-gcp?action=enroll) :sweat_smile:\n  3. [The Neural Aesthetic @ SchoolOfMa, Summer 2016](https:\u002F\u002Fml4a.github.io\u002Fclasses\u002Fneural-aesthetic\u002F) :rainbow: :bowtie:\n  4. [Machine Learning for Musicians and Artists, Kadenze](https:\u002F\u002Fwww.kadenze.com\u002Fcourses\u002Fmachine-learning-for-musicians-and-artists-i)[Scheduled course] :rainbow: :bowtie:\n  5. [Creative Applications of Deep Learning with TensorFlow, Kadenze](https:\u002F\u002Fwww.kadenze.com\u002Fprograms\u002Fcreative-applications-of-deep-learning-with-tensorflow)[Whole Program] :rainbow: :sweat_smile:\n  6. [Coursera - Machine Learning](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning) :bowtie:\n  7. [Coursera - Neural Networks](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks-deep-learning) :sweat_smile:\n  8. [Practical Deep Learning for Coders](http:\u002F\u002Fwww.fast.ai\u002F2017\u002F02\u002F24\u002Fcaptions-and-notes\u002F) :bowtie:\n  9. [‪Course in Machine Learning](http:\u002F\u002Fciml.info\u002F?utm_source=mybridge&utm_medium=ios&utm_campaign=read_more‬)\n  10. [‪Stanford Course Machine Learning](http:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus.html)\n  11. [Udacity - Machine Learning Engineer](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fmachine-learning-engineer-nanodegree--nd009)[Whole Program] :sweat_smile:\n  12. [DeepMind - Reinforcement Learning lectures by David Silver](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL7-jPKtc4r78-wCZcQn5IqyuWhBZ8fOxT)\n\n## Examples\n  1. [A Deep Q Reinforcement Learning Demo](http:\u002F\u002Fprojects.rajivshah.com\u002Frldemo\u002F) :bowtie:\n  1. [How to use Q Learning in Video Games Easily](https:\u002F\u002Fgithub.com\u002FllSourcell\u002Fq_learning_demo) :rainbow: :bowtie:\n  1. [K-nearest](https:\u002F\u002Ftwitter.com\u002FMaximilianLloyd\u002Fstatus\u002F814942799351185408) :bowtie:\n  1. [The Infinite Drum Machine](https:\u002F\u002Faiexperiments.withgoogle.com\u002Fdrum-machine\u002Fview\u002F) :rainbow: :bowtie:\n  1. [Visualizing various ML algorithms](https:\u002F\u002Fkwichmann.github.io\u002Fml_sandbox\u002F) :rainbow: :bowtie:\n  1. [Image-to-Image - from lines to cats](http:\u002F\u002Faffinelayer.com\u002Fpixsrv\u002F) :rainbow:\n  2. [Recurrent Neural Network Tutorial for Artists](http:\u002F\u002Fblog.otoro.net\u002F2017\u002F01\u002F01\u002Frecurrent-neural-network-artist\u002F) :rainbow:\n  1. [Browser Self-Driving Car](http:\u002F\u002Fjanhuenermann.com\u002Fprojects\u002Flearning-to-drive),[Learning to Drive Blog Post](http:\u002F\u002Flab.janhuenermann.de\u002Farticle\u002Flearning-to-drive)\n  1. [The Neural Network Zoo (cheat sheet of nn architectures)](http:\u002F\u002Fwww.asimovinstitute.org\u002Fneural-network-zoo\u002F)\n  1. [Slice of Machine Learning](https:\u002F\u002Fsliceofml.withgoogle.com\u002F#\u002F)\n\n## Projects\n  1. [Bidirectional LSTM for IMDB sentiment classification](https:\u002F\u002Ftranscranial.github.io\u002Fkeras-js\u002F#\u002Fimdb-bidirectional-lstm) :sweat_smile:\n  1. [Land Lines](https:\u002F\u002Fmedium.com\u002F@zachlieberman\u002Fland-lines-e1f88c745847#.1157xmhw8)\n  1. [nnvis - Topological Visualisation of a Convolutional Neural Network](http:\u002F\u002Fterencebroad.com\u002Fconvnetvis\u002Fvis.html) :rainbow: :bowtie:\n  1. [char-rnn A character level language model (a fancy text generator)](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fchar-rnn) :rainbow: :sweat_smile:\n  1. [Machine Learning Projects](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002FML-to-watch.html)\n\n## Videos\n  * Reinforcement Learning\n    1. [Artificial Intelligence in Google's Dinosaur (English Sub)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P7XHzqZjXQs) :bowtie:\n    1. [How to use Q Learning in Video Games Easily](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=A5eihauRQvo&feature=youtu.be) :bowtie:\n  * Evolutionary Algorithms\n    1. [Evolving Swimming Soft-Bodied Creatures](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4ZqdvYrZ3ro) :rainbow: :bowtie:\n    1. [Harnessing evolutionary creativity: evolving soft-bodied animats in simulated physical environments](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CXTZHHQ7ZiQ&feature=youtu.be) :rainbow: :bowtie:\n    1. [Reproduce image with genetic algorithm](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=iV-hah6xs2A) :bowtie:\n  * Deep Learning\n    1. ‪[Video Lectures of Deep Learning‪](http:\u002F\u002Fvideolectures.net\u002Fdeeplearning2015_montreal\u002F) ‬:sweat_smile:\n    1. [Neural networks class - Université de Sherbrooke](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH)\n    1. ‪[A Friendly Introduction to Machine Learning‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=IpGxLWOIZy4) ‬:bowtie:\n    1. ‪[A friendly introduction to Deep Learning and Neural Networks](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BR9h47Jtqyw&t=837s) ‬:bowtie:\n    1. ‪[A friendly introduction to Convolutional Neural Networks and Image Recognition](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2-Ol7ZB0MmU) ‬:bowtie:\n    1. ‪[Deep Learning Demystified](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Q9Z20HCPnww&t=225s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=4) ‬:bowtie:\n    1. ‪[How Deep Neural Networks Work](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ILsA4nyG7I0&t=1269s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=1) ‬:bowtie:\n    1. ‪[How Convolutional Neural Networks work](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FmpDIaiMIeA&t=700s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=2) :bowtie:\n  * Artificial Intelligence\n    1. [MIT 6.034 Artificial Intelligence, Fall 2010](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63gFHB6xb-kVBiQHYe_4hSi) - Complete set of course lectures\n\n## Resources\n  1. [Awesome Machine Learning](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning)\n  1. ‪[QA StackOverflow Machine Learning Algorithms](http:\u002F\u002Fstackoverflow.com\u002Fquestions\u002F20898300\u002Fwhats-the-other-major-approach-paradigms-in-machine-learning-besides-baysian-me)\n  1. [‪Free dataset for projects](https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002Ffree-datasets-for-projects)\n  1. [Facial Recognition Database](https:\u002F\u002Fwww.kairos.com\u002Fblog\u002F166-60-facial-recognition-databases)\n  1. [iOS application- Read top articles for your professional skills with @mybridge - Here you can find new articles every day for Data Science and Machine Learning among other things](https:\u002F\u002Fitunes.apple.com\u002Fapp\u002Fid1055459116)\n  1. [Machine Learning Resources](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002FML-resources-you-should-know.html)\n  1. [Isochrones using the Google Maps Distance Matrix API](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002Fisochrones-isocronut.html)\n  1. [Index of Best AI\u002FMachine Learning Resources](https:\u002F\u002Fhackernoon.com\u002Findex-of-best-ai-machine-learning-resources-71ba0c73e34d#.f0vx1erj9)\n\n## Newsletter\n  1. [Data Science](https:\u002F\u002Fwww.datascienceweekly.org\u002F)\n  1. [Data Elixir](https:\u002F\u002Fdataelixir.com\u002F)\n  1. [Artificial Intelligence Weekly](http:\u002F\u002Faiweekly.co\u002F)\n  1. [Data Aspirant](http:\u002F\u002Fdataaspirant.com\u002F)\n\n## Tools\n  1. [ConvNetJS - Javascript library for training Deep Learning models (Neural Networks) ](http:\u002F\u002Fcs.stanford.edu\u002Fpeople\u002Fkarpathy\u002Fconvnetjs\u002F) :sweat_smile:\n  1. [RecurrentJS - Deep Recurrent Neural Networks and LSTMs in Javascript](https:\u002F\u002Fgithub.com\u002Fshiffman\u002Frecurrentjs) :sweat_smile:\n  1. [AIXIjs - JavaScript demo for running General Reinforcement Learning (RL) agents](https:\u002F\u002Fgithub.com\u002Faslanides\u002Faixijs\u002F) :sweat_smile:\n  1. [WORD2VEC](http:\u002F\u002Ftechnobium.com\u002Ffind-words-similarity-using-deeplearning4j-word2vec\u002F) :sweat_smile:\n  1. [Neuro.js](https:\u002F\u002Fgithub.com\u002Fjanhuenermann\u002Fneurojs)\n  1. [‪Google Chrome Extensión to download all Image of the Google Search](https:\u002F\u002Fchrome.google.com\u002Fwebstore\u002Fdetail\u002Ffatkun-batch-download-ima\u002Fnnjjahlikiabnchcpehcpkdeckfgnohf?hl=es‬) :bowtie: :rainbow:\n  1 [Scikit-Learn](http:\u002F\u002Fscikit-learn.org\u002F)\n\n### TensorFlow\n  1. [Projector](http:\u002F\u002Fprojector.tensorflow.org\u002F) :sweat_smile:\n  1. [Magenta](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmagenta) :rainbow:\n  1. [TensorFlow and Flask](https:\u002F\u002Fblog.metaflow.fr\u002Ftensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc#.96tvigb98_), Thanks to @Hebali [basic pipeline, minus TensorFlow plus a very basic placeholder function](\nhttp:\u002F\u002Fwww.patrickhebron.com\u002Flearning-machines\u002Fweek8.html)\n  1. [Awesome Tensorflow - curated list of TensorFlow tutorials](https:\u002F\u002Fgithub.com\u002Fjtoy\u002Fawesome-tensorflow)\n\n### Tensorflow posts\n  1. [Big deep learning news: Google Tensorflow chooses Keras](http:\u002F\u002Fwww.fast.ai\u002F2017\u002F01\u002F03\u002Fkeras\u002F)\n  1. [Simple end-to-end TensorFlow examples](http:\u002F\u002Fbcomposes.com\u002F2015\u002F11\u002F26\u002Fsimple-end-to-end-tensorflow-examples\u002F)\n  1. [TensorFlow website Getting Started](https:\u002F\u002Fwww.tensorflow.org\u002Fget_started\u002Fget_started):bowtie:\n\n### t-SNE\n  1. [t-SNE](https:\u002F\u002Flvdmaaten.github.io\u002Ftsne\u002F) :sweat_smile:\n  1. [t-SNE](https:\u002F\u002Fscienceai.github.io\u002Ftsne-js\u002F) :sweat_smile:\n  1. [An illustrated introduction to the t-SNE algorithm](https:\u002F\u002Fwww.oreilly.com\u002Flearning\u002Fan-illustrated-introduction-to-the-t-sne-algorithm)\n  1. [Visualizing Data Using t-SNE](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RJVL80Gg3lA&list=UUtXKDgv1AVoG88PLl8nGXmw) :rainbow:\n","[![CodingTrain 中的梦想](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FCodingTrain_Machine-Learning_readme_9189a9e7e009.jpg)](http:\u002F\u002Fthecodingtrain.com\u002F)\n\n# 机器学习\n为即将发布的 Coding Train 视频和 ITP 课程准备的机器学习示例与实验。\n\n# 资源属性\n\n由于互联网上的资源在先决条件和通用可访问性方面各不相同，因此为它们添加属性会很有帮助，这样可以更容易地理解该资源在整个机器学习领域中的定位。以下是一些建议的属性（请继续补充）：\n\n - :rainbow: = 创意\n - :bowtie: = 初学者\n - :sweat_smile: = 中级，有一定先决条件\n - :godmode: = 高级，需要较多先决条件\n\n# 目录\n\u003C!-- MarkdownTOC depth=4 -->\n- [文章与帖子](#articles--posts)\n- [书籍](#books)\n- [课程](#courses)\n- [示例](#examples)\n- [项目](#projects)\n- [视频](#videos)\n- [资源](#resources)\n- [新闻通讯](#newsletter)\n- [工具](#tools)\n    - [TensorFlow](#tensorflow)\n    - [t-SNE](#t-sne)\n\n\u003C!-- \u002FMarkdownTOC -->\n## 文章与帖子\n  1. [重返机器学习](https:\u002F\u002Fmedium.com\u002F@kcimc\u002Fa-return-to-machine-learning-2de3728558eb#.vlqnbo9yg) :rainbow: :bowtie:\n  1. [机器学习视觉入门](http:\u002F\u002Fwww.r2d3.us\u002Fvisual-intro-to-machine-learning-part-1\u002F) :rainbow: :bowtie:\n  1. [机器学习真有趣！](https:\u002F\u002Fmedium.com\u002F@ageitgey\u002Fmachine-learning-is-fun-80ea3ec3c471) :bowtie:\n  1. [深度强化学习：从像素中玩 Pong 游戏](http:\u002F\u002Fkarpathy.github.io\u002F2016\u002F05\u002F31\u002Frl\u002F) :rainbow:\n  1. [揭秘 Libratus，这款击败顶级人类玩家的扑克 AI](https:\u002F\u002Fwww.wired.com\u002F2017\u002F02\u002Flibratus\u002F?imm_mid=0ed017&cmp=em-data-na-na-newsltr_ai_20170206) :bowtie:\n  1. [JavaScript 中的机器学习：简介](http:\u002F\u002Fburakkanber.com\u002Fblog\u002Fmachine-learning-in-other-languages-introduction\u002F) :bowtie:\n  1. [基于字符的长短期记忆循环神经网络实时控制序列生成](http:\u002F\u002Fwww.iggi.org.uk\u002Fassets\u002FIGGI-2016-Memo-A.pdf) :sweat_smile:\n  1. [为什么机器学习“很难”？](http:\u002F\u002Fai.stanford.edu\u002F~zayd\u002Fwhy-is-machine-learning-hard.html) :bowtie:\n  1. [RNN 的不合理有效性](http:\u002F\u002Fkarpathy.github.io\u002F2015\u002F05\u002F21\u002Frnn-effectiveness\u002F) :sweat_smile:\n  1. [colah 的博客](http:\u002F\u002Fcolah.github.io\u002F)\n  1. [拥有大量机器学习教程的机器学习网站](https:\u002F\u002Fmachinelearningmastery.com\u002Fstart-here\u002F) :rainbow:\n  1. [决策树实现初学者教程](https:\u002F\u002Fwww.dezyre.com\u002Fdata-science-in-r-programming-tutorial\u002Fdecision-tree-tutorial) :rainbow:\n  1. [机器学习初学者教程：监督学习与无监督学习](http:\u002F\u002Fdataaspirant.com\u002F2014\u002F09\u002F19\u002Fsupervised-and-unsupervised-learning\u002F) :rainbow:\n  1. [Q 学习教程](http:\u002F\u002Foutlace.com\u002Frlpart3.html) :sweat_smile:\n  1. [Free Code Camp 的大 O 表示法](https:\u002F\u002Fmedium.freecodecamp.com\u002Ftime-is-complex-but-priceless-f0abd015063c?source=linkShare-4599aaae9f0b-1489449307) :bowtie:\n  1. [Ray Wenderlich 的大 O 表示法](https:\u002F\u002Fgithub.com\u002Fraywenderlich\u002Fswift-algorithm-club\u002Fblob\u002Fmaster\u002FBig-O%20Notation.markdown) :bowtie:\n  1. [Interview Cake 的大 O 表示法](https:\u002F\u002Fwww.interviewcake.com\u002Farticle\u002Fjava\u002Fbig-o-notation-time-and-space-complexity) :bowtie:\n  1. [Derek Banas 的 YouTube 视频：大 O 表示法](https:\u002F\u002Fm.youtube.com\u002Fwatch?v=V6mKVRU1evU) :bowtie:\n  1. [HackerRank 的 YouTube 视频：大 O 表示法](https:\u002F\u002Fyoutu.be\u002Fv4cd1O4zkGw) :bowtie:\n  1. [Python 中的随机森林](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002Frandom-forests-in-python.html) :sweat_smile:\n  1. [CreativeAI - 关于创造力的民主化与升级](https:\u002F\u002Fmedium.com\u002F@creativeai\u002Fcreativeai-9d4b2346faf3#.8oaibcklb) :rainbow: :bowtie:\n  1. [使用神经网络降低数据维度](https:\u002F\u002Fwww.cs.toronto.edu\u002F~hinton\u002Fscience.pdf)\n  1. [学习用于人工智能的深度架构](https:\u002F\u002Fwww.iro.umontreal.ca\u002F~bengioy\u002Fpapers\u002Fftml.pdf)\n  1. [让我们从头开始编写一个神经网络（Processing）](https:\u002F\u002Fmedium.com\u002Ftypeme\u002Flets-code-a-neural-network-from-scratch-part-1-24f0a30d7d62) :sweat_smile:\n  1. [Distill - 解密机器学习研究](http:\u002F\u002Fdistill.pub\u002F)\n  1. [JavaScript 中的机器学习](http:\u002F\u002Fburakkanber.com\u002Ftag\u002Fml-in-js\u002F) :sweat_smile:\n  1. [谷歌的人工智能实验](https:\u002F\u002Faiexperiments.withgoogle.com\u002F)\n  1. [Rohan & Lenny #3：循环神经网络与 LSTM](https:\u002F\u002Fayearofai.com\u002Frohan-lenny-3-recurrent-neural-networks-10300100899b) :sweat_smile:\n  1. [LSTM 的反向传播：一个数值示例](https:\u002F\u002Fmedium.com\u002F@aidangomez\u002Flet-s-do-this-f9b699de31d9) :sweat_smile:\n  1. [傻瓜版朴素贝叶斯；简单解释](http:\u002F\u002Fblog.aylien.com\u002Fnaive-bayes-for-dummies-a-simple-explanation\u002F) :bowtie:\n  1. [伯克利大学的机器学习速成班](https:\u002F\u002Fml.berkeley.edu\u002Fblog\u002Ftutorials\u002F) :bowtie: :godmode:\n  1. [如何解决几乎任何机器学习问题？](http:\u002F\u002Fblog.kaggle.com\u002F2016\u002F07\u002F21\u002Fapproaching-almost-any-machine-learning-problem-abhishek-thakur\u002F) :sweat_smile:\n  1. [Chris Albon 的机器学习与人工智能技术笔记](https:\u002F\u002Fchrisalbon.com\u002F#machine_learning) :bowtie: :sweat_smile:\n  1. [朴素贝叶斯与文本分类](https:\u002F\u002Fsebastianraschka.com\u002FArticles\u002F2014_naive_bayes_1.html) :sweat_smile:\n  1. [首次接触 TensorFlow](https:\u002F\u002Ftorres.ai\u002Fresearch-teaching\u002Ftensorflow\u002Ffirst-contact-with-tensorflow-book\u002Ffirst-contact-with-tensorflow\u002F) :sweat_smile:\n\n## 书籍\n  1. [设计师的机器学习](http:\u002F\u002Fwww.oreilly.com\u002Fdesign\u002Ffree\u002Fmachine-learning-for-designers.csp) 由 [Patrick Hebron](http:\u002F\u002Fwww.patrickhebron.com\u002F) 编写，[配套网络研讨会：机器学习与设计的未来](http:\u002F\u002Fwww.oreilly.com\u002Fpub\u002Fe\u002F3709)\n  1. [机器学习书籍](https:\u002F\u002Fmachinelearningmastery.com\u002Fmaster-machine-learning-algorithms\u002F) :rainbow:\n  1. [初次接触机器学习](https:\u002F\u002Fwww.ics.uci.edu\u002F~welling\u002Fteaching\u002FICS273Afall11\u002FIntroMLBook.pdf) :bowtie:\n  1. [使用 Python 进行自然语言处理](https:\u002F\u002Fwww.nltk.org\u002Fbook\u002F) :sweat_smile: :bowtie:\n  1. [神经网络简要介绍](http:\u002F\u002Fwww.dkriesel.com\u002Fen\u002Fscience\u002Fneural_networks) :sweat_smile:\n\n## 课程\n  1. [Google机器学习速成课](https:\u002F\u002Fdevelopers.google.com\u002Fmachine-learning\u002Fcrash-course\u002F) :bowtie:\n  2. [Coursera - 使用TensorFlow在GCP上进行机器学习](https:\u002F\u002Fwww.coursera.org\u002Fspecializations\u002Fmachine-learning-tensorflow-gcp?action=enroll) :sweat_smile:\n  3. [Neural Aesthetic @ SchoolOfMa，2016年夏季](https:\u002F\u002Fml4a.github.io\u002Fclasses\u002Fneural-aesthetic\u002F) :rainbow: :bowtie:\n  4. [面向音乐家和艺术家的机器学习，Kadenze](https:\u002F\u002Fwww.kadenze.com\u002Fcourses\u002Fmachine-learning-for-musicians-and-artists-i)[已安排课程] :rainbow: :bowtie:\n  5. [使用TensorFlow的深度学习创意应用，Kadenze](https:\u002F\u002Fwww.kadenze.com\u002Fprograms\u002Fcreative-applications-of-deep-learning-with-tensorflow)[完整课程] :rainbow: :sweat_smile:\n  6. [Coursera - 机器学习](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fmachine-learning) :bowtie:\n  7. [Coursera - 神经网络](https:\u002F\u002Fwww.coursera.org\u002Flearn\u002Fneural-networks-deep-learning) :sweat_smile:\n  8. [面向编码者的实用深度学习](http:\u002F\u002Fwww.fast.ai\u002F2017\u002F02\u002F24\u002Fcaptions-and-notes\u002F) :bowtie:\n  9. [机器学习课程](http:\u002F\u002Fciml.info\u002F?utm_source=mybridge&utm_medium=ios&utm_campaign=read_more‬)\n  10. [斯坦福大学机器学习课程](http:\u002F\u002Fcs229.stanford.edu\u002Fsyllabus.html)\n  11. [Udacity - 机器学习工程师](https:\u002F\u002Fwww.udacity.com\u002Fcourse\u002Fmachine-learning-engineer-nanodegree--nd009)[完整课程] :sweat_smile:\n  12. [DeepMind - 大卫·西尔弗的强化学习讲座](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL7-jPKtc4r78-wCZcQn5IqyuWhBZ8fOxT)\n\n## 示例\n  1. [深度Q强化学习演示](http:\u002F\u002Fprojects.rajivshah.com\u002Frldemo\u002F) :bowtie:\n  1. [如何轻松地在视频游戏中使用Q学习](https:\u002F\u002Fgithub.com\u002FllSourcell\u002Fq_learning_demo) :rainbow: :bowtie:\n  1. [K近邻](https:\u002F\u002Ftwitter.com\u002FMaximilianLloyd\u002Fstatus\u002F814942799351185408) :bowtie:\n  1. [无限鼓机](https:\u002F\u002Faiexperiments.withgoogle.com\u002Fdrum-machine\u002Fview\u002F) :rainbow: :bowtie:\n  1. [可视化各种机器学习算法](https:\u002F\u002Fkwichmann.github.io\u002Fml_sandbox\u002F) :rainbow: :bowtie:\n  1. [图像到图像 - 从线条到猫咪](http:\u002F\u002Faffinelayer.com\u002Fpixsrv\u002F) :rainbow:\n  2. [面向艺术家的循环神经网络教程](http:\u002F\u002Fblog.otoro.net\u002F2017\u002F01\u002F01\u002Frecurrent-neural-network-artist\u002F) :rainbow:\n  1. [浏览器自动驾驶汽车](http:\u002F\u002Fjanhuenermann.com\u002Fprojects\u002Flearning-to-drive),[学习驾驶博客文章](http:\u002F\u002Flab.janhuenermann.de\u002Farticle\u002Flearning-to-drive)\n  1. [神经网络动物园（神经网络架构速查表）](http:\u002F\u002Fwww.asimovinstitute.org\u002Fneural-network-zoo\u002F)\n  1. [机器学习切片](https:\u002F\u002Fsliceofml.withgoogle.com\u002F#\u002F)\n\n## 项目\n  1. [用于IMDB情感分类的双向LSTM](https:\u002F\u002Ftranscranial.github.io\u002Fkeras-js\u002F#\u002Fimdb-bidirectional-lstm) :sweat_smile:\n  1. [陆地线条](https:\u002F\u002Fmedium.com\u002F@zachlieberman\u002Fland-lines-e1f88c745847#.1157xmhw8)\n  1. [nnvis - 卷积神经网络的拓扑可视化](http:\u002F\u002Fterencebroad.com\u002Fconvnetvis\u002Fvis.html) :rainbow: :bowtie:\n  1. [char-rnn 字符级语言模型（一个花哨的文本生成器）](https:\u002F\u002Fgithub.com\u002Fkarpathy\u002Fchar-rnn) :rainbow: :sweat_smile:\n  1. [机器学习项目](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002FML-to-watch.html)\n\n## 视频\n  * 强化学习\n    1. [谷歌恐龙中的人工智能（英文字幕）](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=P7XHzqZjXQs) :bowtie:\n    1. [如何轻松地在视频游戏中使用Q学习](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=A5eihauRQvo&feature=youtu.be) :bowtie:\n  * 进化算法\n    1. [进化出游泳的软体生物](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=4ZqdvYrZ3ro) :rainbow: :bowtie:\n    1. [利用进化创造力：在模拟物理环境中进化软体动画机器人](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=CXTZHHQ7ZiQ&feature=youtu.be) :rainbow: :bowtie:\n    1. [用遗传算法重现图像](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=iV-hah6xs2A) :bowtie:\n  * 深度学习\n    1. ‪[深度学习视频讲座‪](http:\u002F\u002Fvideolectures.net\u002Fdeeplearning2015_montreal\u002F) ‬:sweat_smile:\n    1. [舍布鲁克大学神经网络课程](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PL6Xpj9I5qXYEcOhn7TqghAJ6NAPrNmUBH)\n    1. ‪[机器学习友好入门‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=IpGxLWOIZy4) ‬:bowtie:\n    1. ‪[深度学习和神经网络友好入门‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=BR9h47Jtqyw&t=837s) ‬:bowtie:\n    1. ‪[卷积神经网络和图像识别友好入门‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=2-Ol7ZB0MmU) ‬:bowtie:\n    1. ‪[深度学习揭秘‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Q9Z20HCPnww&t=225s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=4) ‬:bowtie:\n    1. ‪[深层神经网络的工作原理‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=ILsA4nyG7I0&t=1269s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=1) ‬:bowtie:\n    1. ‪[卷积神经网络的工作原理‪](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=FmpDIaiMIeA&t=700s&list=PLVZqlMpoM6kbaeySxhdtgQPFEC5nV7Faa&index=2) :bowtie:\n  * 人工智能\n    1. [MIT 6.034人工智能，2010年秋季](https:\u002F\u002Fwww.youtube.com\u002Fplaylist?list=PLUl4u3cNGP63gFHB6xb-kVBiQHYe_4hSi) - 完整的课程讲座\n\n## 资源\n  1. [Awesome Machine Learning](https:\u002F\u002Fgithub.com\u002Fjosephmisiti\u002Fawesome-machine-learning)\n  1. ‪[StackOverflow机器学习算法问答](http:\u002F\u002Fstackoverflow.com\u002Fquestions\u002F20898300\u002Fwhats-the-other-major-approach-paradigms-in-machine-learning-besides-baysian-me)\n  1. [项目免费数据集](https:\u002F\u002Fwww.dataquest.io\u002Fblog\u002Ffree-datasets-for-projects)\n  1. [面部识别数据库](https:\u002F\u002Fwww.kairos.com\u002Fblog\u002F166-60-facial-recognition-databases)\n  1. [iOS应用 - 使用@mybridge阅读提升专业技能的热门文章 - 在这里每天都能找到关于数据科学和机器学习等方面的新文章](https:\u002F\u002Fitunes.apple.com\u002Fapp\u002Fid1055459116)\n  1. [机器学习资源](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002FML-resources-you-should-know.html)\n  1. [使用Google地图距离矩阵API的等时线](http:\u002F\u002Fblog.yhat.com\u002Fposts\u002Fisochrones-isocronut.html)\n  1. [最佳AI\u002F机器学习资源索引](https:\u002F\u002Fhackernoon.com\u002Findex-of-best-ai-machine-learning-resources-71ba0c73e34d#.f0vx1erj9)\n\n## 新闻简报\n  1. [数据科学](https:\u002F\u002Fwww.datascienceweekly.org\u002F)\n  1. [Data Elixir](https:\u002F\u002Fdataelixir.com\u002F)\n  1. [人工智能周刊](http:\u002F\u002Faiweekly.co\u002F)\n  1. [数据 aspirant](http:\u002F\u002Fdataaspirant.com\u002F)\n\n## 工具\n  1. [ConvNetJS - 用于训练深度学习模型（神经网络）的 JavaScript 库](http:\u002F\u002Fcs.stanford.edu\u002Fpeople\u002Fkarpathy\u002Fconvnetjs\u002F) :sweat_smile:\n  1. [RecurrentJS - JavaScript 中的深度循环神经网络和 LSTM](https:\u002F\u002Fgithub.com\u002Fshiffman\u002Frecurrentjs) :sweat_smile:\n  1. [AIXIjs - 运行通用强化学习（RL）智能体的 JavaScript 演示](https:\u002F\u002Fgithub.com\u002Faslanides\u002Faixijs\u002F) :sweat_smile:\n  1. [WORD2VEC](http:\u002F\u002Ftechnobium.com\u002Ffind-words-similarity-using-deeplearning4j-word2vec\u002F) :sweat_smile:\n  1. [Neuro.js](https:\u002F\u002Fgithub.com\u002Fjanhuenermann\u002Fneurojs)\n  1. [Google Chrome 扩展程序，用于下载 Google 搜索中的所有图片](https:\u002F\u002Fchrome.google.com\u002Fwebstore\u002Fdetail\u002Ffatkun-batch-download-ima\u002Fnnjjahlikiabnchcpehcpkdeckfgnohf?hl=es‬) :bowtie: :rainbow:\n  1 [Scikit-Learn](http:\u002F\u002Fscikit-learn.org\u002F)\n\n### TensorFlow\n  1. [Projector](http:\u002F\u002Fprojector.tensorflow.org\u002F) :sweat_smile:\n  1. [Magenta](https:\u002F\u002Fgithub.com\u002Ftensorflow\u002Fmagenta) :rainbow:\n  1. [TensorFlow 与 Flask](https:\u002F\u002Fblog.metaflow.fr\u002Ftensorflow-how-to-freeze-a-model-and-serve-it-with-a-python-api-d4f3596b3adc#.96tvigb98_), 感谢 @Hebali 提供的[基础流程，去掉了 TensorFlow，只保留了一个非常简单的占位符函数](\nhttp:\u002F\u002Fwww.patrickhebron.com\u002Flearning-machines\u002Fweek8.html)\n  1. [Awesome Tensorflow - 精选的 TensorFlow 教程列表](https:\u002F\u002Fgithub.com\u002Fjtoy\u002Fawesome-tensorflow)\n\n### TensorFlow 相关文章\n  1. [深度学习重大新闻：Google TensorFlow 选择 Keras](http:\u002F\u002Fwww.fast.ai\u002F2017\u002F01\u002F03\u002Fkeras\u002F)\n  1. [简单的端到端 TensorFlow 示例](http:\u002F\u002Fbcomposes.com\u002F2015\u002F11\u002F26\u002Fsimple-end-to-end-tensorflow-examples\u002F)\n  1. [TensorFlow 官网入门指南](https:\u002F\u002Fwww.tensorflow.org\u002Fget_started\u002Fget_started):bowtie:\n\n### t-SNE\n  1. [t-SNE](https:\u002F\u002Flvdmaaten.github.io\u002Ftsne\u002F) :sweat_smile:\n  1. [t-SNE](https:\u002F\u002Fscienceai.github.io\u002Ftsne-js\u002F) :sweat_smile:\n  1. [t-SNE 算法的图解介绍](https:\u002F\u002Fwww.oreilly.com\u002Flearning\u002Fan-illustrated-introduction-to-the-t-sne-algorithm)\n  1. [使用 t-SNE 可视化数据](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RJVL80Gg3lA&list=UUtXKDgv1AVoG88PLl8nGXmw) :rainbow:","# Machine-Learning 资源库快速上手指南\n\n## 简介\n本仓库（Machine-Learning）并非一个可直接安装的软件库或框架，而是由 **Coding Train** 维护的机器学习**学习资源索引**。它汇集了适合初学者到高级开发者的文章、书籍、课程、代码示例和项目链接，特别侧重于创意编码（Creative Coding）和艺术应用。\n\n本指南将指导你如何利用该仓库开始你的机器学习学习之旅。\n\n## 环境准备\n\n由于本仓库主要是资源列表，无需特定的系统环境即可浏览。但为了运行其中推荐的代码示例（通常基于 Python 或 JavaScript），建议准备以下基础环境：\n\n### 系统要求\n- 操作系统：Windows \u002F macOS \u002F Linux\n- 浏览器：现代浏览器（Chrome, Firefox, Edge）用于查看在线演示和教程\n\n### 前置依赖（针对实操练习）\n大多数示例涉及以下技术栈，建议提前安装：\n\n1.  **Python 环境** (推荐版本 3.8+)\n    *   用于运行 TensorFlow, Keras, PyTorch 等示例。\n2.  **Node.js** (可选)\n    *   用于运行部分 JavaScript\u002FProcessing.js 相关的创意编码示例。\n3.  **Git**\n    *   用于克隆具体的示例项目代码。\n\n**安装 Python 示例 (使用国内镜像源加速):**\n```bash\n# Windows\u002FmacOS\u002FLinux 通用建议：前往 python.org 下载或使用包管理器\n# 国内用户推荐使用清华源配置 pip\npip config set global.index-url https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 获取与浏览步骤\n\n本仓库的核心价值在于其分类整理的资源列表。你可以通过以下步骤开始学习：\n\n### 1. 访问仓库\n直接访问 GitHub 页面浏览目录：\n*   **地址**: `https:\u002F\u002Fgithub.com\u002FCodingTrain\u002FMachine-Learning`\n\n### 2. 选择学习路径\n根据 README 中的难度标识选择适合你的资源：\n*   🌈 **:rainbow: Creative** - 创意类项目，适合艺术家和设计师。\n*   👔 **:bowtie: Beginner** - 入门级，无需深厚数学背景。\n*   😅 **:sweat_smile: Intermediate** - 进阶级，需要一定编程和数学基础。\n*   😎 **:godmode: Advanced** - 高级，需要大量前置知识。\n\n### 3. 克隆具体示例项目 (实操)\n当你找到感兴趣的具体项目链接（例如 `char-rnn` 或 `q_learning_demo`）时，通常需要克隆该项目到本地运行。\n\n**通用克隆命令：**\n```bash\ngit clone \u003C项目仓库的 URL>\ncd \u003C项目文件夹名称>\n```\n\n**安装该项目特定依赖（以 Python 项目为例）：**\n```bash\n# 进入项目目录后\npip install -r requirements.txt\n```\n\n## 基本使用示例\n\n假设你对 **\"强化学习 (Reinforcement Learning)\"** 感兴趣，并希望运行一个简单的演示：\n\n### 第一步：定位资源\n在仓库的 [Examples](#examples) 或 [Videos](#videos) 部分找到：\n*   项目名：*How to use Q Learning in Video Games Easily*\n*   难度：👔 (:bowtie: Beginner) \u002F 🌈 (:rainbow: Creative)\n*   链接指向：`https:\u002F\u002Fgithub.com\u002FllSourcell\u002Fq_learning_demo`\n\n### 第二步：获取代码\n在终端执行：\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FllSourcell\u002Fq_learning_demo.git\ncd q_learning_demo\n```\n\n### 第三步：运行示例\n根据该项目具体的 `README` 指示运行（通常为 Python 脚本）：\n```bash\n# 安装依赖\npip install -r requirements.txt\n\n# 运行演示\npython demo.py\n```\n*(注：具体文件名需参考该项目内部的说明)*\n\n### 第四步：深入学习\n回到主仓库，点击对应的 [Courses](#courses) 链接（如 Google 的 Machine Learning Crash Course 或 Coursera 专项课程），系统性地补充理论知识。\n\n---\n**提示**：本仓库是动态更新的索引，建议将其加入书签，定期查看新的 [Articles & Posts](#articles--posts) 和 [Tools](#tools) 更新。","一位创意编程讲师正准备制作一期关于“用神经网络生成诗歌”的视频教程，急需向零基础观众直观解释复杂的机器学习概念。\n\n### 没有 Machine-Learning 时\n- 讲师需要在海量且良莠不齐的网络资源中盲目搜索，难以区分哪些文章适合初学者，哪些需要深厚的数学背景。\n- 缺乏统一的难度标识，容易误选高阶论文作为素材，导致视频内容过于晦涩，观众因听不懂而流失。\n- 找不到将机器学习与艺术创作（如诗歌、绘画）结合的生动案例，只能枯燥地讲解算法公式，无法激发观众兴趣。\n- 整理教学大纲耗时极长，需手动验证每个链接的有效性和内容匹配度，严重拖慢视频制作进度。\n\n### 使用 Machine-Learning 后\n- 直接利用仓库中的标签系统（如 :bowtie: 代表入门，:rainbow: 代表创意），瞬间筛选出既简单又具艺术感的教程资源。\n- 精准定位到《Machine Learning is Fun!》或《A Visual Introduction to Machine Learning》等可视化强、门槛低的文章，确保内容通俗易懂。\n- 引用仓库中收录的“字符级循环神经网络生成序列”等创意项目案例，让抽象算法在视频中转化为生动的诗歌创作演示。\n- 依托现成的目录结构快速构建课程逻辑，从基础概念到实战代码一气呵成，大幅缩短备课与视频制作周期。\n\nMachine-Learning 通过结构化分类与创意导向的资源整合，让复杂的技术教学变得清晰有趣，极大提升了知识传播的效率与感染力。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FCodingTrain_Machine-Learning_bf307a03.png","CodingTrain","Coding Train","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FCodingTrain_6948912b.jpg","Accompanying code and more for YouTube video tutorials",null,"thecodingtrain","http:\u002F\u002Fthecodingtrain.com","https:\u002F\u002Fgithub.com\u002FCodingTrain",1008,196,"2026-04-11T03:13:52",1,"","未说明",{"notes":29,"python":27,"dependencies":30},"该仓库并非一个可直接运行的单一软件工具，而是一个机器学习学习资源合集（包含文章、书籍、课程、示例代码链接等）。因此，README 中未提供具体的操作系统、硬件配置或依赖库版本要求。具体的运行环境需求取决于用户选择学习的特定示例或项目（如部分示例可能涉及 TensorFlow、Keras 或 JavaScript 等），需参考各个独立资源的文档。",[],[32],"其他",2,"ready","2026-03-27T02:49:30.150509","2026-04-20T10:22:48.245849",[],[],[40,56,64,72,81,89],{"id":41,"name":42,"github_repo":43,"description_zh":44,"stars":45,"difficulty_score":33,"last_commit_at":46,"category_tags":47,"status":34},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。",85267,"2026-04-18T11:00:28",[48,49,50,51,52,32,53,54,55],"图像","数据工具","视频","插件","Agent","语言模型","开发框架","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":25,"last_commit_at":62,"category_tags":63,"status":34},5784,"funNLP","fighting41love\u002FfunNLP","funNLP 是一个专为中文自然语言处理（NLP）打造的超级资源库，被誉为\"NLP 民工的乐园”。它并非单一的软件工具，而是一个汇集了海量开源项目、数据集、预训练模型和实用代码的综合性平台。\n\n面对中文 NLP 领域资源分散、入门门槛高以及特定场景数据匮乏的痛点，funNLP 提供了“一站式”解决方案。这里不仅涵盖了分词、命名实体识别、情感分析、文本摘要等基础任务的标准工具，还独特地收录了丰富的垂直领域资源，如法律、医疗、金融行业的专用词库与数据集，甚至包含古诗词生成、歌词创作等趣味应用。其核心亮点在于极高的全面性与实用性，从基础的字典词典到前沿的 BERT、GPT-2 模型代码，再到高质量的标注数据和竞赛方案，应有尽有。\n\n无论是刚刚踏入 NLP 领域的学生、需要快速验证想法的算法工程师，还是从事人工智能研究的学者，都能在这里找到急需的“武器弹药”。对于开发者而言，它能大幅减少寻找数据和复现模型的时间；对于研究者，它提供了丰富的基准测试资源和前沿技术参考。funNLP 以开放共享的精神，极大地降低了中文自然语言处理的开发与研究成本，是中文 AI 社区不可或缺的宝藏仓库。",79857,"2026-04-08T20:11:31",[53,49,32],{"id":65,"name":66,"github_repo":67,"description_zh":68,"stars":69,"difficulty_score":25,"last_commit_at":70,"category_tags":71,"status":34},5773,"cs-video-courses","Developer-Y\u002Fcs-video-courses","cs-video-courses 是一个精心整理的计算机科学视频课程清单，旨在为自学者提供系统化的学习路径。它汇集了全球知名高校（如加州大学伯克利分校、新南威尔士大学等）的完整课程录像，涵盖从编程基础、数据结构与算法，到操作系统、分布式系统、数据库等核心领域，并深入延伸至人工智能、机器学习、量子计算及区块链等前沿方向。\n\n面对网络上零散且质量参差不齐的教学资源，cs-video-courses 解决了学习者难以找到成体系、高难度大学级别课程的痛点。该项目严格筛选内容，仅收录真正的大学层级课程，排除了碎片化的简短教程或商业广告，确保用户能接触到严谨的学术内容。\n\n这份清单特别适合希望夯实计算机基础的开发者、需要补充特定领域知识的研究人员，以及渴望像在校生一样系统学习计算机科学的自学者。其独特的技术亮点在于分类极其详尽，不仅包含传统的软件工程与网络安全，还细分了生成式 AI、大语言模型、计算生物学等新兴学科，并直接链接至官方视频播放列表，让用户能一站式获取高质量的教育资源，免费享受世界顶尖大学的课堂体验。",79792,"2026-04-08T22:03:59",[32,48,49,54],{"id":73,"name":74,"github_repo":75,"description_zh":76,"stars":77,"difficulty_score":78,"last_commit_at":79,"category_tags":80,"status":34},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",[52,48,54,53,32],{"id":82,"name":83,"github_repo":84,"description_zh":85,"stars":86,"difficulty_score":78,"last_commit_at":87,"category_tags":88,"status":34},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。",75940,"2026-04-19T21:42:30",[53,48,54,32],{"id":90,"name":91,"github_repo":92,"description_zh":93,"stars":94,"difficulty_score":25,"last_commit_at":95,"category_tags":96,"status":34},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,"2026-04-03T21:50:24",[54,32]]