新智元推薦

來源：專知 （ID：Quan_Zhuanzhi）

作者：Robbie Allen

整理：Sanglei, Shengsheng

【新智元導讀】本文收集並詳細篩選出了一系列機器學習、自然語言處理、Python及數學基礎知識的相關資源和教程，數目多達200種！來源既包括斯坦福、MIT等名校，也有Github、Medium等熱門網站上的技術教程和資料，篩選原則是內容盡量涵蓋精華要點，避免重複。乾貨滿滿的一篇教程匯總，強烈建議大家收藏學習！

去年，我寫了一份相當受歡迎的博文(在Medium上有16萬閱讀量，見相關資源1)，列出了我在深入研究大量機器學習資源時發現的最佳教程。十三個月後，現在有許多關於傳統機器學習概念的新教程大量湧現以及過去一年中出現的新技術。圍繞機器學習持續增加的大量內容有著驚人的數量。

本文包含了迄今為止我發現的最好的一些教程內容。它絕不是網上每個機器學習相關教程的簡單詳盡列表（這個工作量無疑是十分巨大而又枯燥重複的），而是經過詳細篩選後的結果。我的目標就是將我在機器學習和自然語言處理領域各個方面找到的我認為最好的教程整理出來。

在教程中，為了能夠更好的讓讀者理解其中的概念，我將避免羅列書中每章的詳細內容，而是總結一些概念性的介紹內容。為什麼不直接去買本書？當你想要對某些特定的主題或者不同方面進行了初步了解時，我相信這些教程對你可能幫助更大。

本文中我將分四個主題進行整理: 機器學習，自然語言處理，Python和數學。在每個主題中我將包含一個例子和多個資源。當然我不可能完全覆蓋所有的主題啦。

如果你發現我在這裡遺漏了好的教程資源，請聯繫告訴我。為了避免資源重複羅列，我在每個主題下只列出了5、6個教程。下面的每個鏈接都應該鏈接了和其他鏈接不同的資源，也會通過不同的方式（例如幻燈片代碼段)或者不同的角度呈現出這些內容。

相關資源

本文作者Robbie Allen是以為科技作者和創業者、並自學AI並成為博士生。曾整理許多廣為流傳的機器學習相關資源。

1. 2017版教程資源 Over 150 ofthe Best Machine Learning, NLP, and Python Tutorials I』ve Found（150多個最好的與機器學習,自然語言處理和Python相關的教程）

• 英文：

  https://medium.com/machine-learning-in-practice/over-150-of-the-best-machine-learning-nlp-and-python-tutorials-ive-found-ffce2939bd78

• 中文翻譯：http://pytlab.org

2. My Curated List of AI and Machine LearningResources from Around the Web( 終極收藏AI領域你不能不關注的大牛、機構、課程、會議、圖書)

• 英文：

  https://medium.com/machine-learning-in-practice/my-curated-list-of-ai-and-machine-learning-resources-from-around-the-web-9a97823b8524

• 中文翻譯：

  http://www.sohu.com/a/168291972_473283

3. Cheat Sheet of Machine Learningand Python (and Math) Cheat Sheets

（值得收藏的27 個機器學習速查表）

• 英文：

  https://medium.com/machine-learning-in-practice/cheat-sheet-of-machine-learning-and-python-and-math-cheat-sheets-a4afe4e791b6

目錄

第一部分：機器學習

• Start Here with Machine Learning (machinelearningmastery.com)

  https://machinelearningmastery.com/start-here/

• Machine Learning is Fun! (medium.com/@ageitgey)

  https://medium.com/@ageitgey/machine-learning-is-fun-80ea3ec3c471

• Machine Learning CrashCourse: Part I, Part II, Part III (Machine Learning atBerkeley)

• Part I https://ml.berkeley.edu/blog/2016/11/06/tutorial-1/

• Part II https://ml.berkeley.edu/blog/2016/12/24/tutorial-2/

• Part III https://ml.berkeley.edu/blog/2017/02/04/tutorial-3/

• An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples (toptal.com)

  https://www.toptal.com/machine-learning/machine-learning-theory-an-introductory-primer

• A Gentle Guide to Machine Learning (monkeylearn.com)

  https://monkeylearn.com/blog/a-gentle-guide-to-machine-learning/

• Which machine learning algorithm should I use? (sas.com)

  https://blogs.sas.com/content/subconsciousmusings/2017/04/12/machine-learning-algorithm-use/

• The Machine Learning Primer (sas.com)

  https://www.sas.com/content/dam/SAS/en_us/doc/whitepaper1/machine-learning-primer-108796.pdf

• Machine Learning Tutorial for Beginners (kaggle.com/kanncaa1)

  https://www.kaggle.com/kanncaa1/machine-learning-tutorial-for-beginners

1.1 激活函數與損失函數

• What is the role of the activation function in a neural network? (quora.com)

  https://www.quora.com/What-is-the-role-of-the-activation-function-in-a-neural-network

• Comprehensive list of activation functions in neural networks with pros/cons(stats.stackexchange.com)

  https://stats.stackexchange.com/questions/115258/comprehensive-list-of-activation-functions-in-neural-networks-with-pros-cons

• Activation functions and it』stypes-Which is better? (medium.com)

  https://medium.com/towards-data-science/activation-functions-and-its-types-which-is-better-a9a5310cc8f

1.2 偏差(bias)

• Role of Bias in Neural Networks (stackoverflow.com)

  https://stackoverflow.com/questions/2480650/role-of-bias-in-neural-networks/2499936#2499936

• What is bias in artificial neural network? (quora.com)

  https://www.quora.com/What-is-bias-in-artificial-neural-network

1.3 感知機（perceptron）

• Single-layer Neural Networks(Perceptrons) (dcu.ie)

  http://computing.dcu.ie/~humphrys/Notes/Neural/single.neural.html

• From Perceptrons to Deep Networks (toptal.com)

  https://www.toptal.com/machine-learning/an-introduction-to-deep-learning-from-perceptrons-to-deep-networks

1.4 回歸（Regression）

• Introduction to linear regression analysis (duke.edu)

  http://people.duke.edu/~rnau/regintro.htm

• Linear Regression (readthedocs.io)

  http://ml-cheatsheet.readthedocs.io/en/latest/linear_regression.html

• Logistic Regression (readthedocs.io)

  http://ml-cheatsheet.readthedocs.io/en/latest/logistic_regression.html

1.5 梯度下降（Gradient Descent）1.6 生成學習（Generative Learning）

• A practical explanation of aNaive Bayes classifier (monkeylearn.com)

  https://monkeylearn.com/blog/practical-explanation-naive-bayes-classifier/

1.7 支持向量機（Support Vector Machines）

• An introduction to SupportVector Machines (SVM) (monkeylearn.com)

  https://monkeylearn.com/blog/introduction-to-support-vector-machines-svm/

1.8 反向傳播（Backpropagation）

• Yes you should understandbackprop (medium.com/@karpathy)

  https://medium.com/@karpathy/yes-you-should-understand-backprop-e2f06eab496b

• Can you give a visualexplanation for the back propagation algorithm for neural networks? (github.com/rasbt)

  https://github.com/rasbt/python-machine-learning-book/blob/master/faq/visual-backpropagation.md

• Backpropagation Through Timeand Vanishing Gradients (wildml.com)

  http://www.wildml.com/2015/10/recurrent-neural-networks-tutorial-part-3-backpropagation-through-time-and-vanishing-gradients/

1.9 深度學習（Deep Learning）

• A Guide to Deep Learning byYN2 (yerevann.com)

  http://yerevann.com/a-guide-to-deep-learning/

• Deep Learning Papers ReadingRoadmap (github.com/floodsung)

  https://github.com/floodsung/Deep-Learning-Papers-Reading-Roadmap

• A Tutorial on DeepLearning (Quoc V. Le)

  http://ai.stanford.edu/~quocle/tutorial1.pdf

• What is DeepLearning? (machinelearningmastery.com)

  http://machinelearningmastery.com/what-is-deep-learning/

• What』s the Difference BetweenArtificial Intelligence, Machine Learning, and Deep Learning? (nvidia.com)

  https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial-intelligence-machine-learning-deep-learning-ai/

• Deep Learning—TheStraight Dope (gluon.mxnet.io)

  https://gluon.mxnet.io/

1.10 優化與降維（Optimization and Dimensionality Reduction）

• Seven Techniques for DataDimensionality Reduction (knime.org)

  https://www.knime.org/blog/seven-techniques-for-data-dimensionality-reduction

1.11 Long Short Term Memory (LSTM)

• A Gentle Introduction to LongShort-Term Memory Networks by the Experts (machinelearningmastery.com)

  http://machinelearningmastery.com/gentle-introduction-long-short-term-memory-networks-experts/

1.12 卷積神經網路 Convolutional Neural Networks (CNNs)

• Deep Learning and Convolutional Neural Networks (medium.com/@ageitgey)

  https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721

1.13 循環神經網路 Recurrent Neural Nets (RNNs)1.14 強化學習 Reinforcement Learning

• Simple Beginner』s guide toReinforcement Learning & its implementation (analyticsvidhya.com)

  https://www.analyticsvidhya.com/blog/2017/01/introduction-to-reinforcement-learning-implementation/

• A Tutorial for ReinforcementLearning (mst.edu)

  https://web.mst.edu/~gosavia/tutorial.pdf

1.15 生成對抗模型 Generative Adversarial Networks (GANs)

• Adversarial MachineLearning (aaai18adversarial.github.io)

  https://aaai18adversarial.github.io/slides/AML.pptx

• What』s a Generative AdversarialNetwork? (nvidia.com)

  https://blogs.nvidia.com/blog/2017/05/17/generative-adversarial-network/

• Abusing Generative AdversarialNetworks to Make 8-bit Pixel Art (medium.com/@ageitgey)

  https://medium.com/@ageitgey/abusing-generative-adversarial-networks-to-make-8-bit-pixel-art-e45d9b96cee7

• An introduction to GenerativeAdversarial Networks (with code in TensorFlow) (aylien.com)

  http://blog.aylien.com/introduction-generative-adversarial-networks-code-tensorflow/

• Generative Adversarial Networksfor Beginners (oreilly.com)

  https://www.oreilly.com/learning/generative-adversarial-networks-for-beginners

1.16 多任務學習 Multi-task Learning

第二部分：自然語言處理

• Natural Language Processing isFun! (medium.com/@ageitgey)

  https://medium.com/@ageitgey/natural-language-processing-is-fun-9a0bff37854e

• A Primer on Neural Network Models for Natural Language Processing (Yoav Goldberg)

  http://u.cs.biu.ac.il/~yogo/nnlp.pdf

• The Definitive Guide to NaturalLanguage Processing (monkeylearn.com)

  https://monkeylearn.com/blog/the-definitive-guide-to-natural-language-processing/

• Introduction to NaturalLanguage Processing (algorithmia.com)

  https://blog.algorithmia.com/introduction-natural-language-processing-nlp/

• Natural Language Processing(almost) from Scratch (arxiv.org)

  https://arxiv.org/pdf/1103.0398.pdf

2.1 深度學習與自然語言處理 Deep Learning and NLP

• Deep Learning applied toNLP (arxiv.org)

  https://arxiv.org/pdf/1703.03091.pdf

• Deep Learning for NLP (withoutMagic) (Richard Socher)

  https://nlp.stanford.edu/courses/NAACL2013/NAACL2013-Socher-Manning-DeepLearning.pdf

• Embed, encode, attend, predict:The new deep learning formula for state-of-the-art NLPmodels (explosion.ai)

  https://explosion.ai/blog/deep-learning-formula-nlp

• Understanding Natural Languagewith Deep Neural Networks Using Torch(nvidia.com)

  https://devblogs.nvidia.com/parallelforall/understanding-natural-language-deep-neural-networks-using-torch/

2.2 詞向量 Word Vectors

• Bag of Words Meets Bags ofPopcorn (kaggle.com)

  https://www.kaggle.com/c/word2vec-nlp-tutorial

• On word embeddings PartI, Part II, Part III (sebastianruder.com)

• Part I :http://sebastianruder.com/word-embeddings-1/index.html

• Part II:http://sebastianruder.com/word-embeddings-softmax/index.html

• Part III: http://sebastianruder.com/secret-word2vec/index.html

• The amazing power of wordvectors (acolyer.org)

  https://blog.acolyer.org/2016/04/21/the-amazing-power-of-word-vectors/

• word2vec Parameter LearningExplained (arxiv.org)

  https://arxiv.org/pdf/1411.2738.pdf

2.3 編解碼模型 Encoder-Decoder

• Sequence to SequenceModels (tensorflow.org)

  https://www.tensorflow.org/tutorials/seq2seq

• Sequence to Sequence Learningwith Neural Networks (NIPS 2014)

  https://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf

• Machine Learning is Fun Part 5:Language Translation with Deep Learning and the Magic ofSequences (medium.com/@ageitgey)

  https://medium.com/@ageitgey/machine-learning-is-fun-part-5-language-translation-with-deep-learning-and-the-magic-of-sequences-2ace0acca0aa

• How to use an Encoder-DecoderLSTM to Echo Sequences of Random Integers(machinelearningmastery.com)

  http://machinelearningmastery.com/how-to-use-an-encoder-decoder-lstm-to-echo-sequences-of-random-integers/

• tf-seq2seq (google.github.io)

  https://google.github.io/seq2seq/

第三部分：Python

• Machine Learning CrashCourse (google.com)

  https://developers.google.com/machine-learning/crash-course/

• Awesome MachineLearning (github.com/josephmisiti)

  https://github.com/josephmisiti/awesome-machine-learning#python

• An example machine learningnotebook (nbviewer.jupyter.org)

  http://nbviewer.jupyter.org/github/rhiever/Data-Analysis-and-Machine-Learning-Projects/blob/master/example-data-science-notebook/Example%20Machine%20Learning%20Notebook.ipynb

• Machine Learning withPython (tutorialspoint.com)

  https://www.tutorialspoint.com/machine_learning_with_python/machine_learning_with_python_quick_guide.htm

3.1 樣例 Examples

• ML fromScatch (github.com/eriklindernoren)

  https://github.com/eriklindernoren/ML-From-Scratch

• Python Machine Learning (2ndEd.) Code Repository (github.com/rasbt)

  https://github.com/rasbt/python-machine-learning-book-2nd-edition

3.2 Scipy and numpy教程

• Scipy LectureNotes (scipy-lectures.org)

  http://www.scipy-lectures.org/

• An introduction to Numpy andScipy (UCSB CHE210D)

  https://engineering.ucsb.edu/~shell/che210d/numpy.pdf

3.3 scikit-learn教程

• scikit-learn ClassificationAlgorithms (github.com/mmmayo13)

  https://github.com/mmmayo13/scikit-learn-classifiers/blob/master/sklearn-classifiers-tutorial.ipynb

• scikit-learnTutorials (scikit-learn.org)

  http://scikit-learn.org/stable/tutorial/index.html

• Abridged scikit-learnTutorials (github.com/mmmayo13)

  https://github.com/mmmayo13/scikit-learn-beginners-tutorials

3.4 Tensorflow教程

• Tensorflow Tutorials (tensorflow.org)

  https://www.tensorflow.org/tutorials/

• Introduction to TensorFlow—CPUvs GPU (medium.com/@erikhallstrm)

  https://medium.com/@erikhallstrm/hello-world-tensorflow-649b15aed18c

• TensorFlow: Aprimer (metaflow.fr)

  https://blog.metaflow.fr/tensorflow-a-primer-4b3fa0978be3

3.5 PyTorch教程

• Tutorial: Deep Learning inPyTorch (iamtrask.github.io)

  https://iamtrask.github.io/2017/01/15/pytorch-tutorial/

• PyTorch Examples (github.com/jcjohnson)

  https://github.com/jcjohnson/pytorch-examples

• PyTorchTutorial (github.com/MorvanZhou)

  https://github.com/MorvanZhou/PyTorch-Tutorial

• PyTorch Tutorial for DeepLearning Researchers (github.com/yunjey)

  https://github.com/yunjey/pytorch-tutorial

第四部分：數學基礎知識

• Math for MachineLearning (ucsc.edu)

  https://people.ucsc.edu/~praman1/static/pub/math-for-ml.pdf

• Math for MachineLearning (UMIACS CMSC422)

  http://www.umiacs.umd.edu/~hal/courses/2013S_ML/math4ml.pdf

4.1 線性代數

• An Intuitive Guide to LinearAlgebra (betterexplained.com)

  https://betterexplained.com/articles/linear-algebra-guide/

• A Programmer』s Intuition forMatrix Multiplication (betterexplained.com)

  https://betterexplained.com/articles/matrix-multiplication/

• Understanding the Cross Product (betterexplained.com)

  https://betterexplained.com/articles/cross-product/

• Understanding the DotProduct (betterexplained.com)

  https://betterexplained.com/articles/vector-calculus-understanding-the-dot-product/

• Linear Algebra for MachineLearning (U. of Buffalo CSE574)

  http://www.cedar.buffalo.edu/~srihari/CSE574/Chap1/LinearAlgebra.pdf

• Linear algebra cheat sheet fordeep learning (medium.com)

  https://medium.com/towards-data-science/linear-algebra-cheat-sheet-for-deep-learning-cd67aba4526c

4.2 概率論

• Understanding Bayes TheoremWith Ratios (betterexplained.com)

  https://betterexplained.com/articles/understanding-bayes-theorem-with-ratios/

• Probability Theory Review forMachine Learning (Stanford CS229)

  https://see.stanford.edu/materials/aimlcs229/cs229-prob.pdf

• Probability Theory (U. ofBuffalo CSE574)

  http://www.cedar.buffalo.edu/~srihari/CSE574/Chap1/Probability-Theory.pdf

• Probability Theory for MachineLearning (U. of Toronto CSC411)

  http://www.cs.toronto.edu/~urtasun/courses/CSC411_Fall16/tutorial1.pdf

4.3 微積分

• How To Understand Derivatives:The Quotient Rule, Exponents, and Logarithms (betterexplained.com)

  https://betterexplained.com/articles/how-to-understand-derivatives-the-quotient-rule-exponents-and-logarithms/

• How To Understand Derivatives:The Product, Power & Chain Rules(betterexplained.com)

  https://betterexplained.com/articles/derivatives-product-power-chain/

• Vector Calculus: Understandingthe Gradient (betterexplained.com)

  https://betterexplained.com/articles/vector-calculus-understanding-the-gradient/

• CalculusOverview (readthedocs.io)

  http://ml-cheatsheet.readthedocs.io/en/latest/calculus.html

原文鏈接：

https://medium.com/machine-learning-in-practice/over-200-of-the-best-machine-learning-nlp-and-python-tutorials-2018-edition-dd8cf53cb7dc

本文經授權轉載自微信公眾號「專知」（ID：Quan_Zhuanzhi）

新智元AI WORLD 2018大會【早鳥票】開售！

新智元將於9月20日在北京國家會議中心舉辦AI WORLD 2018 大會，邀請機器學習教父、CMU教授 Tom Mitchell，邁克思·泰格馬克，周志華，陶大程，陳怡然等AI領袖一起關注機器智能與人類命運。

大會官網：

http://www.aiworld2018.com/

即日起到8月19日，新智元限量發售若干早鳥票，與全球AI領袖近距離交流，見證全球人工智慧產業跨越發展。

喜歡這篇文章嗎？立刻分享出去讓更多人知道吧！