干货 | 请收下这份2018学习清单：150个最好的机器学习，NLP和Python教程

本文英文出处：Robbie Allen

翻译/吴楚

校对/田晋阳

 

机器学习的发展可以追溯到1959年，有着丰富的历史。这个领域也正在以前所未有的速度进化。在之前的一篇文章（https://unsupervisedmethods.com/why-artificial-intelligence-is-different-from-previous-technology-waves-764d7710df8b）中，我们讨论过为什么通用人工智能领域即将要爆发。有兴趣入坑ML的小伙伴不要拖延了，时不我待！

 

在今年秋季开始准备博士项目的时候，我已经精选了一些有关机器学习和NLP的优质网络资源。一般我会找一个有意思的教程或者视频，再由此找到三四个，甚至更多的教程或者视频。猛回头，发现标收藏夹又多了20个资源待我学习（推荐提升效率工具Tab Bundler）。

 

找到超过25个有关ML的“小抄”后，我写一篇博文（https://unsupervisedmethods.com/cheat-sheet-of-machine-learning-and-python-and-math-cheat-sheets-a4afe4e791b6），里面的资源都有超链接。

 

为了帮助也在经历类似探索过程的童鞋，我把至今发现的最好的教程汇总了一个列表。当然这不是网络上有关ML的最全集合，而且其中有一部分内容很普通。我的目标是要找到最好的有关机器学习子方向和NLP的教程。

 

我引用了能简洁介绍概念的基础内容。我已经回避包含一些大部头书的章节，和对理解概念没有帮助的科研论文。那为什么不买一本书呢？ 因为教程能更好地帮助你学一技之长或者打开新视野。

 

我把这博文分成四个部分，机器学习，NLP，Python，和数学基础。在每一小节我会随机引入一些问题。由于这方面学习材料太丰富了，本文并未涵括所有内容。

     机器学习

1、机器学习就是这么好玩！(medium.com/@ageitgey)

 

机器学习速成课程（Berkeley的ML）：

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/

 

机器学习入门与应用：实例图解(toptal.com)

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

 

机器学习的简易指南 (monkeylearn.com)

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

 

如何选择机器学习算法？(sas.com)

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

 

2、Activation and Loss Functions

激活函数与损失函数

sigmoid 神经元 (neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap1.html#sigmoid_neurons

 

激活函数在神经网络中有什么作用？(quora.com)

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

 

神经网络的激活函数大全及其优劣 (stats.stackexchange.com)

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

 

激活函数及其分类比较(medium.com)

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

 

理解对数损失 (exegetic.biz)

http://www.exegetic.biz/blog/2015/12/making-sense-logarithmic-loss/

 

损失函数(Stanford CS231n)

http://cs231n.github.io/neural-networks-2/#losses

 

损失函数L1 与L2 比较(rishy.github.io)

http://rishy.github.io/ml/2015/07/28/l1-vs-l2-loss/

 

交叉熵损失函数(neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap3.html#the_cross-entropy_cost_function

 

3、偏差（Bias）

神经网络中的偏差的作用(stackoverflow.com)

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

 

神经网络中的偏差节点(makeyourownneuralnetwork.blogspot.com)

http://makeyourownneuralnetwork.blogspot.com/2016/06/bias-nodes-in-neural-networks.html

 

什么是人工神经网络中的偏差 (quora.com)

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

 

4、感知器（Perceptron）

感知器模型(neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap1.html#perceptrons

 

感知器(natureofcode.com)

http://natureofcode.com/book/chapter-10-neural-networks/#chapter10_figure3

 

一层的神经网络（感知器模型）(dcu.ie)

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

 

从感知器模型到深度网络(toptal.com)

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

 

5、回归算法

线性回归分析简介(duke.edu)

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

 

线性回归 (ufldl.stanford.edu)

http://ufldl.stanford.edu/tutorial/supervised/LinearRegression/

 

线性回归 (readthedocs.io)

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

 

逻辑斯特回归 (readthedocs.io)

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

 

机器学习之简单线性回归教程(machinelearningmastery.com)

http://machinelearningmastery.com/simple-linear-regression-tutorial-for-machine-learning/

 

机器学习之逻辑斯特回归教程(machinelearningmastery.com)

http://machinelearningmastery.com/logistic-regression-tutorial-for-machine-learning/

 

softmax 回归(ufldl.stanford.edu)

http://ufldl.stanford.edu/tutorial/supervised/SoftmaxRegression/

 

6、梯度下降

基于梯度下降的学习 (neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap1.html#learning_with_gradient_descent

 

梯度下降(iamtrask.github.io)

http://iamtrask.github.io/2015/07/27/python-network-part2/

 

如何理解梯度下降算法？(kdnuggets.com)

http://www.kdnuggets.com/2017/04/simple-understand-gradient-descent-algorithm.html

 

梯度下降优化算法概览(sebastianruder.com)

http://sebastianruder.com/optimizing-gradient-descent/

 

优化算法：随机梯度下降算法 (Stanford CS231n)

http://cs231n.github.io/optimization-1/

 

7、生成学习

 

生成学习算法 (Stanford CS229)

http://cs229.stanford.edu/notes/cs229-notes2.pdf

 

贝叶斯分类算法之实例解析(monkeylearn.com)

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

 

8、支持向量机

 

支持向量机（SVM）入门(monkeylearn.com)

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

 

支持向量机(Stanford CS229)

http://cs229.stanford.edu/notes/cs229-notes3.pdf

 

线性分类：支持向量机，Softmax (Stanford 231n)

http://cs231n.github.io/linear-classify/

 

9、后向传播算法（Backpropagation）

 

后向传播算法必知(medium.com/@karpathy)

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

 

来，给我图解一下神经网络后向传播算法？(github.com/rasbt)

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

 

后向传播算法是如何运行的？(neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap2.html

 

沿时后向传播算法与梯度消失(wildml.com)

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

 

简易入门沿时后向传播算法(machinelearningmastery.com)

http://machinelearningmastery.com/gentle-introduction-backpropagation-time/

 

奔跑吧，后向传播算法！(Stanford CS231n)

http://cs231n.github.io/optimization-2/

 

10、深度学习

 

果壳里的深度学习(nikhilbuduma.com)

http://nikhilbuduma.com/2014/12/29/deep-learning-in-a-nutshell/

 

深度学习教程 (Quoc V. Le)

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

 

深度学习，什么鬼？(machinelearningmastery.com)

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

 

什么是人工智能，机器学习，深度学习之间的区别？ (nvidia.com)

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

 

11、优化算法与降维算法

 

数据降维的七招炼金术(knime.org)

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

 

主成分分析(Stanford CS229)

http://cs229.stanford.edu/notes/cs229-notes10.pdf

 

Dropout: 改进神经网络的一个简单方法(Hinton @ NIPS 2012)

http://videolectures.net/site/normal_dl/tag=741100/nips2012_hinton_networks_01.pdf

 

如何溜你们家的深度神经网络？(rishy.github.io)

http://rishy.github.io/ml/2017/01/05/how-to-train-your-dnn/

 

12、长短期记忆(LSTM) 

老司机带你简易入门长短期神经网络(machinelearningmastery.com)

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

 

理解LSTM网络(colah.github.io)

http://colah.github.io/posts/2015-08-Understanding-LSTMs/

 

漫谈LSTM模型(echen.me)

http://blog.echen.me/2017/05/30/exploring-lstms/

 

小学生看完这教程都可以用Python实现一个LSTM-RNN (iamtrask.github.io)

http://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/

 

13、卷积神经网络（CNNs）

 

卷积网络入门(neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap6.html#introducing_convolutional_networks

 

深度学习与卷积神经网络模型(medium.com/@ageitgey)

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

 

拆解卷积网络模型(colah.github.io)

http://colah.github.io/posts/2014-07-Conv-Nets-Modular/

 

理解卷积网络(colah.github.io)

http://colah.github.io/posts/2014-07-Understanding-Convolutions/

14、递归神经网络(RNNs)

 

递归神经网络教程 (wildml.com)

http://www.wildml.com/2015/09/recurrent-neural-networks-tutorial-part-1-introduction-to-rnns/

 

注意力模型与增强型递归神经网络(distill.pub)

http://distill.pub/2016/augmented-rnns/

 

这么不科学的递归神经网络模型(karpathy.github.io)

http://karpathy.github.io/2015/05/21/rnn-effectiveness/

 

深入递归神经网络模型(nikhilbuduma.com)

http://nikhilbuduma.com/2015/01/11/a-deep-dive-into-recurrent-neural-networks/

 15、强化学习

 

给小白看的强化学习及其实现指南 (analyticsvidhya.com)

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

 

强化学习教程(mst.edu)

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

 

强化学习，你学了么？(wildml.com)

http://www.wildml.com/2016/10/learning-reinforcement-learning/

 

深度强化学习：开挂玩Pong (karpathy.github.io)

http://karpathy.github.io/2016/05/31/rl/

 

16、对抗式生成网络模型(GANs)

 

什么是对抗式生成网络模型？(nvidia.com)

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

 

用对抗式生成网络创造8个像素的艺术(medium.com/@ageitgey)

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

 

对抗式生成网络入门（TensorFlow）(aylien.com)

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

 

《对抗式生成网络》（小学一年级~上册）(oreilly.com)

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

 

17、多任务学习

深度神经网络中的多任务学习概述(sebastianruder.com)

http://sebastianruder.com/multi-task/index.html

  NLP

‍

1、NLP

《基于神经网络模型的自然语言处理》（小学一年级~上册）(Yoav Goldberg)

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

 

自然语言处理权威指南(monkeylearn.com)

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

 

自然语言处理入门(algorithmia.com)

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

 

自然语言处理教程 (vikparuchuri.com)

http://www.vikparuchuri.com/blog/natural-language-processing-tutorial/

 

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

初高中生课程：自然语言处理 (arxiv.org)

https://arxiv.org/pdf/1103.0398.pdf  

2、深度学习和 NLP

基于深度学习的NLP应用(arxiv.org)

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

 

基于深度学习的NLP(Richard Socher)

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

 

理解卷积神经网络在NLP中的应用(wildml.com)

http://www.wildml.com/2015/11/understanding-convolutional-neural-networks-for-nlp/

 

深度学习，NLP，表示学习(colah.github.io)

http://colah.github.io/posts/2014-07-NLP-RNNs-Representations/

 

嵌入表示，编码，注意力，预测 : 新一代深度学习因NLP的精妙而存在(explosion.ai)

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

 

理解基于神经网络的自然语言处理(Torch实现) (nvidia.com)

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

 

深度学习在NLP中的应用(Pytorch实现) (pytorich.org)

http://pytorch.org/tutorials/beginner/deep_learning_nlp_tutorial.html

 

 3、词向量（Word Vectors）

 

词袋法遇到感知器装袋法(kaggle.com)

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

 

学习单词嵌入表示法(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

 

单词嵌入表示的神奇力量(acolyer.org)

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

 

解释word2vec 的参数学习(arxiv.org)

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

 

word2vec教程 skip-gram 模型，负采样(mccormickml.com)

http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/

 

4、Encoder-Decoder

 

注意力机制与记忆机制在深度学习与NLP中的应用(wildml.com)

http://www.wildml.com/2016/01/attention-and-memory-in-deep-learning-and-nlp/

 

序列到序列模型(tensorflow.org)

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

 

利用神经网络学习序列到序列模型(NIPS 2014)

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

 

基于深度学习和魔法序列的语言翻译(medium.com/@ageitgey)

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

 

如何使用编码-解码LSTM输出随机整数对应的序列(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/

 

   Python

1、Python

使用Python精通机器学习的七步法(kdnuggets.com)

http://www.kdnuggets.com/2015/11/seven-steps-machine-learning-python.html

 

机器学习的一个简例(nbviewer.jupyter.org)

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

2、实例

小白如何用python实现感知器算法(machinelearningmastery.com)

http://machinelearningmastery.com/implement-perceptron-algorithm-scratch-python/

 

小学生用python实现一个神经网络(wildml.com)

http://www.wildml.com/2015/09/implementing-a-neural-network-from-scratch/

 

只用11行python代码实现一个神经网络算法(iamtrask.github.io)

http://iamtrask.github.io/2015/07/12/basic-python-network/

 

自己动手用ptython实现最近邻算法(kdnuggets.com)

http://www.kdnuggets.com/2016/01/implementing-your-own-knn-using-python.html

 

python实现长短期记忆网络的记忆机制(machinelearningmastery.com)

http://machinelearningmastery.com/memory-in-a-long-short-term-memory-network/

 

如何用长短期记忆递归神经网络输出随机整数(machinelearningmastery.com)

http://machinelearningmastery.com/learn-echo-random-integers-long-short-term-memory-recurrent-neural-networks/

 

如何用seq2seq递归神经网络学习加法运算(machinelearningmastery.com)

http://machinelearningmastery.com/learn-add-numbers-seq2seq-recurrent-neural-networks/

 

3、Scipy 和 numpy

 

Scipy课程笔记(scipy-lectures.org)

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

 

Python Numpy 教程(Stanford CS231n)

http://cs231n.github.io/python-numpy-tutorial/

 

Numpy 与 Scipy 入门(UCSB CHE210D)

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

 

给科学家看的Python微课程(nbviewer.jupyter.org)

http://nbviewer.jupyter.org/gist/rpmuller/5920182#ii.-numpy-and-scipy

 

4、scikit-learn

 

PyCon会议上的Scik-learn 教程(nbviewer.jupyter.org)

http://nbviewer.jupyter.org/github/jakevdp/sklearn_pycon2015/blob/master/notebooks/Index.ipynb

 

Scikit-learn 中的分类算法(github.com/mmmayo13)

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

 

Scikit-learn教程(scikit-learn.org)

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

 

简明版Scikit-learn教程(github.com/mmmayo13)

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

 

5、Tensorflow

 

Tensorflow教程(tensorflow.org)

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

 

Tensorflow入门--CPU vs GPU

 (medium.com/@erikhallstrm)

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

 

Tensorflow入门(metaflow.fr)

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

 

Tensorflow实现RNNs (wildml.com)

http://www.wildml.com/2016/08/rnns-in-tensorflow-a-practical-guide-and-undocumented-features/

 

Tensorflow实现文本分类CNN模型(wildml.com)

http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/

 

如何用Tensorflow做文本摘要(surmenok.com)

http://pavel.surmenok.com/2016/10/15/how-to-run-text-summarization-with-tensorflow/

 

6、PyTorch

 

Pytorch教程(pytorch.org)

http://pytorch.org/tutorials/

Pytorch快手入门 (gaurav.im)

http://blog.gaurav.im/2017/04/24/a-gentle-intro-to-pytorch/

 

利用Pytorch深度学习教程(iamtrask.github.io)

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

 

Pytorch实战(github.com/jcjohnson)

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

 

PyTorch 教程(github.com/MorvanZhou)

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

 

深度学习研究人员看的PyTorch教程(github.com/yunjey)

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

 

   数学

1、机器学习中的数学 (ucsc.edu)

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

 

机器学习数学基础(UMIACS CMSC422)

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

 

2、线性代数

 

线性代数简明指南(betterexplained.com)

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

 

码农眼中矩阵乘法 (betterexplained.com)

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

 

理解叉乘运算(betterexplained.com)

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

 

理解点乘运算(betterexplained.com)

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

 

机器学习中的线性代数(U. of Buffalo CSE574)

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

 

深度学习的线代小抄(medium.com)

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

 

复习线性代数与课后阅读材料(Stanford CS229)

http://cs229.stanford.edu/section/cs229-linalg.pdf

 

3、概率论

 

贝叶斯理论 (betterexplained.com)

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

 

理解贝叶斯概率理论(Stanford CS229)

http://cs229.stanford.edu/section/cs229-prob.pdf

 

复习机器学习中的概率论(Stanford CS229)

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

 

概率论(U. of Buffalo CSE574)

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

 

机器学习中的概率论(U. of Toronto CSC411)

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

4、计算方法（Calculus）

 

如何理解导数：求导法则，指数和算法(betterexplained.com)

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

 

如何理解导数，乘法，幂指数，链式法(betterexplained.com)

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

 

向量计算，理解梯度(betterexplained.com)

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

 

微分计算(Stanford CS224n)

http://web.stanford.edu/class/cs224n/lecture_notes/cs224n-2017-review-differential-calculus.pdf

 

计算方法概论(readthedocs.io)

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

为帮助对自然语言处理感兴趣的同学快速高效入门，AI慕课学院特邀新加坡南洋理工大学博士玖强老师，为大家带来《NLP工程师入门实践班：基于深度学习的自然语言处理》，课程包含NLP三大知识模块，算法理论+案例实训，搭配典型行业应用，层层递进，直通自然语言处理的本质及其应用！

早鸟价799元倒计时3天！！

更有组团优惠，4人成团每人优惠200元，快来组团报名吧！