來(lái)源/AI慕課（ID:MOOC1024）

本文英文出處：Robbie Allen

翻譯/吳楚

校對(duì)/田晉陽(yáng)

機(jī)器學(xué)習(xí)的發(fā)展可以追溯到1959年啥供，有著豐富的歷史。這個(gè)領(lǐng)域也正在以前所未有的速度進(jìn)化薄翅。在之前的一篇文章（https://unsupervisedmethods.com/why-artificial-intelligence-is-different-from-previous-technology-waves-764d7710df8b）中沙兰，我們討論過(guò)為什么通用人工智能領(lǐng)域即將要爆發(fā)。有興趣入坑ML的小伙伴不要拖延了翘魄，時(shí)不我待鼎天！

在秋季開(kāi)始準(zhǔn)備博士項(xiàng)目的時(shí)候，我已經(jīng)精選了一些有關(guān)機(jī)器學(xué)習(xí)和NLP的優(yōu)質(zhì)網(wǎng)絡(luò)資源熟丸。一般我會(huì)找一個(gè)有意思的教程或者視頻训措，再由此找到三四個(gè)，甚至更多的教程或者視頻光羞。猛回頭绩鸣，發(fā)現(xiàn)標(biāo)收藏夾又多了20個(gè)資源待我學(xué)習(xí)（推薦提升效率工具Tab Bundler）。

找到超過(guò)25個(gè)有關(guān)ML的“小抄”后纱兑，我寫(xiě)一篇博文（https://unsupervisedmethods.com/cheat-sheet-of-machine-learning-and-python-and-math-cheat-sheets-a4afe4e791b6）呀闻，里面的資源都有超鏈接。

為了幫助也在經(jīng)歷類(lèi)似探索過(guò)程的童鞋潜慎，我把至今發(fā)現(xiàn)的最好的教程匯總了一個(gè)列表捡多。當(dāng)然這不是網(wǎng)絡(luò)上有關(guān)ML的最全集合，而且其中有一部分內(nèi)容很普通铐炫。我的目標(biāo)是要找到最好的有關(guān)機(jī)器學(xué)習(xí)子方向和NLP的教程垒手。

我引用了能簡(jiǎn)潔介紹概念的基礎(chǔ)內(nèi)容。我已經(jīng)回避包含一些大部頭書(shū)的章節(jié)倒信，和對(duì)理解概念沒(méi)有幫助的科研論文科贬。那為什么不買(mǎi)一本書(shū)呢？ 因?yàn)榻坛棠芨玫貛椭銓W(xué)一技之長(zhǎng)或者打開(kāi)新視野鳖悠。

我把這博文分成四個(gè)部分榜掌，機(jī)器學(xué)習(xí)，NLP乘综，Python憎账，和數(shù)學(xué)基礎(chǔ)。在每一小節(jié)我會(huì)隨機(jī)引入一些問(wèn)題卡辰。由于這方面學(xué)習(xí)材料太豐富了胞皱，本文并未涵括所有內(nèi)容。

機(jī)器學(xué)習(xí)

1九妈、機(jī)器學(xué)習(xí)就是這么好玩朴恳！(medium.com/@ageitgey)

機(jī)器學(xué)習(xí)速成課程（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/

機(jī)器學(xué)習(xí)入門(mén)與應(yīng)用：實(shí)例圖解(toptal.com)

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

機(jī)器學(xué)習(xí)的簡(jiǎn)易指南 (monkeylearn.com)

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

如何選擇機(jī)器學(xué)習(xí)算法？(sas.com)

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

2允蚣、Activation and Loss Functions

激活函數(shù)與損失函數(shù)

sigmoid 神經(jīng)元 (neuralnetworksanddeeplearning.com)

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

激活函數(shù)在神經(jīng)網(wǎng)絡(luò)中有什么作用？(quora.com)

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

神經(jīng)網(wǎng)絡(luò)的激活函數(shù)大全及其優(yōu)劣 (stats.stackexchange.com)

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

激活函數(shù)及其分類(lèi)比較(medium.com)

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

理解對(duì)數(shù)損失 (exegetic.biz)

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

損失函數(shù)(Stanford CS231n)

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

損失函數(shù)L1 與L2 比較(rishy.github.io)

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

交叉熵?fù)p失函數(shù)(neuralnetworksanddeeplearning.com)

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

3呆贿、偏差（Bias）

神經(jīng)網(wǎng)絡(luò)中的偏差的作用(stackoverflow.com)

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

神經(jīng)網(wǎng)絡(luò)中的偏差節(jié)點(diǎn)(makeyourownneuralnetwork.blogspot.com)

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

什么是人工神經(jīng)網(wǎng)絡(luò)中的偏差 (quora.com)

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

4嚷兔、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

一層的神經(jīng)網(wǎng)絡(luò)（感知器模型）(dcu.ie)

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

從感知器模型到深度網(wǎng)絡(luò)(toptal.com)

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

5森渐、回歸算法

線(xiàn)性回歸分析簡(jiǎn)介(duke.edu)

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

線(xiàn)性回歸 (ufldl.stanford.edu)

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

線(xiàn)性回歸 (readthedocs.io)

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

邏輯斯特回歸 (readthedocs.io)

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

機(jī)器學(xué)習(xí)之簡(jiǎn)單線(xiàn)性回歸教程(machinelearningmastery.com)

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

機(jī)器學(xué)習(xí)之邏輯斯特回歸教程(machinelearningmastery.com)

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

softmax 回歸(ufldl.stanford.edu)

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

6、梯度下降

基于梯度下降的學(xué)習(xí) (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冒晰？(kdnuggets.com)

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

梯度下降優(yōu)化算法概覽(sebastianruder.com)

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

優(yōu)化算法：隨機(jī)梯度下降算法 (Stanford CS231n)

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

7同衣、生成學(xué)習(xí)

生成學(xué)習(xí)算法 (Stanford CS229)

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

貝葉斯分類(lèi)算法之實(shí)例解析(monkeylearn.com)

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

8、支持向量機(jī)

支持向量機(jī)（SVM）入門(mén)(monkeylearn.com)

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

支持向量機(jī)(Stanford CS229)

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

線(xiàn)性分類(lèi)：支持向量機(jī)壶运，Softmax (Stanford 231n)

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

9耐齐、后向傳播算法（Backpropagation）

后向傳播算法必知(medium.com/@karpathy)

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

來(lái)，給我圖解一下神經(jīng)網(wǎng)絡(luò)后向傳播算法蒋情？(github.com/rasbt)

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

后向傳播算法是如何運(yùn)行的埠况？(neuralnetworksanddeeplearning.com)

http://neuralnetworksanddeeplearning.com/chap2.html

沿時(shí)后向傳播算法與梯度消失(wildml.com)

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

簡(jiǎn)易入門(mén)沿時(shí)后向傳播算法(machinelearningmastery.com)

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

奔跑吧，后向傳播算法棵癣！(Stanford CS231n)

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

10辕翰、深度學(xué)習(xí)

果殼里的深度學(xué)習(xí)(nikhilbuduma.com)

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

深度學(xué)習(xí)教程 (Quoc V. Le)

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

深度學(xué)習(xí)，什么鬼狈谊？(machinelearningmastery.com)

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

什么是人工智能喜命，機(jī)器學(xué)習(xí)，深度學(xué)習(xí)之間的區(qū)別河劝？ (nvidia.com)

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

11壁榕、優(yōu)化算法與降維算法

數(shù)據(jù)降維的七招煉金術(shù)(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: 改進(jìn)神經(jīng)網(wǎng)絡(luò)的一個(gè)簡(jiǎn)單方法(Hinton @ NIPS 2012)

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

如何溜你們家的深度神經(jīng)網(wǎng)絡(luò)？(rishy.github.io)

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

**12赎瞎、長(zhǎng)短期記憶(LSTM) **

老司機(jī)帶你簡(jiǎn)易入門(mén)長(zhǎng)短期神經(jīng)網(wǎng)絡(luò)(machinelearningmastery.com)

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

理解LSTM網(wǎng)絡(luò)(colah.github.io)

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

漫談LSTM模型(echen.me)

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

小學(xué)生看完這教程都可以用Python實(shí)現(xiàn)一個(gè)LSTM-RNN (iamtrask.github.io)

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

13牌里、卷積神經(jīng)網(wǎng)絡(luò)（CNNs）

卷積網(wǎng)絡(luò)入門(mén)(neuralnetworksanddeeplearning.com)

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

深度學(xué)習(xí)與卷積神經(jīng)網(wǎng)絡(luò)模型(medium.com/@ageitgey)

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

拆解卷積網(wǎng)絡(luò)模型(colah.github.io)

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

理解卷積網(wǎng)絡(luò)(colah.github.io)

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

14、遞歸神經(jīng)網(wǎng)絡(luò)(RNNs)

遞歸神經(jīng)網(wǎng)絡(luò)教程 (wildml.com)

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

注意力模型與增強(qiáng)型遞歸神經(jīng)網(wǎng)絡(luò)(distill.pub)

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

這么不科學(xué)的遞歸神經(jīng)網(wǎng)絡(luò)模型(karpathy.github.io)

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

深入遞歸神經(jīng)網(wǎng)絡(luò)模型(nikhilbuduma.com)

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

** 15煎娇、強(qiáng)化學(xué)習(xí)**

給小白看的強(qiáng)化學(xué)習(xí)及其實(shí)現(xiàn)指南 (analyticsvidhya.com)

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

強(qiáng)化學(xué)習(xí)教程(mst.edu)

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

強(qiáng)化學(xué)習(xí)二庵，你學(xué)了么？(wildml.com)

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

深度強(qiáng)化學(xué)習(xí)：開(kāi)掛玩Pong (karpathy.github.io)

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

16缓呛、對(duì)抗式生成網(wǎng)絡(luò)模型(GANs)

什么是對(duì)抗式生成網(wǎng)絡(luò)模型催享？(nvidia.com)

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

用對(duì)抗式生成網(wǎng)絡(luò)創(chuàng)造8個(gè)像素的藝術(shù)(medium.com/@ageitgey)

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

對(duì)抗式生成網(wǎng)絡(luò)入門(mén)（TensorFlow）(aylien.com)

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

《對(duì)抗式生成網(wǎng)絡(luò)》（小學(xué)一年級(jí)~上冊(cè)）(oreilly.com)

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

17、多任務(wù)學(xué)習(xí)

深度神經(jīng)網(wǎng)絡(luò)中的多任務(wù)學(xué)習(xí)概述(sebastianruder.com)

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

NLP

1哟绊、NLP

《基于神經(jīng)網(wǎng)絡(luò)模型的自然語(yǔ)言處理》（小學(xué)一年級(jí)~上冊(cè)）(Yoav Goldberg)

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

自然語(yǔ)言處理權(quán)威指南(monkeylearn.com)

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

自然語(yǔ)言處理入門(mén)(algorithmia.com)

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

自然語(yǔ)言處理教程 (vikparuchuri.com)

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

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

初高中生課程：自然語(yǔ)言處理 (arxiv.org)

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

2因妙、深度學(xué)習(xí)和 NLP

基于深度學(xué)習(xí)的NLP應(yīng)用(arxiv.org)

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

基于深度學(xué)習(xí)的NLP(Richard Socher)

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

理解卷積神經(jīng)網(wǎng)絡(luò)在NLP中的應(yīng)用(wildml.com)

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

深度學(xué)習(xí)，NLP票髓，表示學(xué)習(xí)(colah.github.io)

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

嵌入表示攀涵，編碼，注意力洽沟，預(yù)測(cè) : 新一代深度學(xué)習(xí)因NLP的精妙而存在(explosion.ai)

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

理解基于神經(jīng)網(wǎng)絡(luò)的自然語(yǔ)言處理(Torch實(shí)現(xiàn)) (nvidia.com)

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

深度學(xué)習(xí)在NLP中的應(yīng)用(Pytorch實(shí)現(xiàn)) (pytorich.org)

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

** 3以故、詞向量（Word Vectors）**

詞袋法遇到感知器裝袋法(kaggle.com)

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

學(xué)習(xí)單詞嵌入表示法(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

單詞嵌入表示的神奇力量(acolyer.org)

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

解釋word2vec 的參數(shù)學(xué)習(xí)(arxiv.org)

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

word2vec教程 skip-gram 模型，負(fù)采樣(mccormickml.com)

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

4裆操、Encoder-Decoder

注意力機(jī)制與記憶機(jī)制在深度學(xué)習(xí)與NLP中的應(yīng)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

利用神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)序列到序列模型(NIPS 2014)

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

基于深度學(xué)習(xí)和魔法序列的語(yǔ)言翻譯(medium.com/@ageitgey)

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

如何使用編碼-解碼LSTM輸出隨機(jī)整數(shù)對(duì)應(yīng)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怒详、 Python

使用Python精通機(jī)器學(xué)習(xí)的七步法(kdnuggets.com)

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

機(jī)器學(xué)習(xí)的一個(gè)簡(jiǎn)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炉媒、實(shí)例

小白如何用python實(shí)現(xiàn)感知器算法(machinelearningmastery.com)

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

小學(xué)生用python實(shí)現(xiàn)一個(gè)神經(jīng)網(wǎng)絡(luò)(wildml.com)

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

只用11行python代碼實(shí)現(xiàn)一個(gè)神經(jīng)網(wǎng)絡(luò)算法(iamtrask.github.io)

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

自己動(dòng)手用ptython實(shí)現(xiàn)最近鄰算法(kdnuggets.com)

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

python實(shí)現(xiàn)長(zhǎng)短期記憶網(wǎng)絡(luò)的記憶機(jī)制(machinelearningmastery.com)

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

如何用長(zhǎng)短期記憶遞歸神經(jīng)網(wǎng)絡(luò)輸出隨機(jī)整數(shù)(machinelearningmastery.com)

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

如何用seq2seq遞歸神經(jīng)網(wǎng)絡(luò)學(xué)習(xí)加法運(yùn)算(machinelearningmastery.com)

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

3、Scipy 和 numpy

Scipy課程筆記(scipy-lectures.org)

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

Python Numpy 教程(Stanford CS231n)

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

Numpy 與 Scipy 入門(mén)(UCSB CHE210D)

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

給科學(xué)家看的Python微課程(nbviewer.jupyter.org)

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

4昆烁、scikit-learn

PyCon會(huì)議上的Scik-learn 教程(nbviewer.jupyter.org)

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

Scikit-learn 中的分類(lèi)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

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

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

5吊骤、Tensorflow

Tensorflow教程(tensorflow.org)

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

Tensorflow入門(mén)--CPU vs GPU

(medium.com/@erikhallstrm)

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

Tensorflow入門(mén)(metaflow.fr)

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

Tensorflow實(shí)現(xiàn)RNNs (wildml.com)

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

Tensorflow實(shí)現(xiàn)文本分類(lèi)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快手入門(mén) (gaurav.im)

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

利用Pytorch深度學(xué)習(xí)教程(iamtrask.github.io)

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

Pytorch實(shí)戰(zhàn)(github.com/jcjohnson)

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

PyTorch 教程(github.com/MorvanZhou)

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

深度學(xué)習(xí)研究人員看的PyTorch教程(github.com/yunjey)

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

數(shù)學(xué)

1静尼、機(jī)器學(xué)習(xí)中的數(shù)學(xué) (ucsc.edu)

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

機(jī)器學(xué)習(xí)數(shù)學(xué)基礎(chǔ)(UMIACS CMSC422)

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

2白粉、線(xiàn)性代數(shù)

線(xiàn)性代數(shù)簡(jiǎn)明指南(betterexplained.com)

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

碼農(nóng)眼中矩陣乘法 (betterexplained.com)

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

理解叉乘運(yùn)算(betterexplained.com)

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

理解點(diǎn)乘運(yùn)算(betterexplained.com)

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

機(jī)器學(xué)習(xí)中的線(xiàn)性代數(shù)(U. of Buffalo CSE574)

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

深度學(xué)習(xí)的線(xiàn)代小抄(medium.com)

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

復(fù)習(xí)線(xiàn)性代數(shù)與課后閱讀材料(Stanford CS229)

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

3、概率論

貝葉斯理論 (betterexplained.com)

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

理解貝葉斯概率理論(Stanford CS229)

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

復(fù)習(xí)機(jī)器學(xué)習(xí)中的概率論(Stanford CS229)

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

概率論(U. of Buffalo CSE574)

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

機(jī)器學(xué)習(xí)中的概率論(U. of Toronto CSC411)

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

4鼠渺、計(jì)算方法（Calculus）

如何理解導(dǎo)數(shù)：求導(dǎo)法則鸭巴，指數(shù)和算法(betterexplained.com)

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

如何理解導(dǎo)數(shù)，乘法系冗，冪指數(shù)奕扣，鏈?zhǔn)椒?betterexplained.com)

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

向量計(jì)算，理解梯度(betterexplained.com)

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

微分計(jì)算(Stanford CS224n)

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

計(jì)算方法概論(readthedocs.io)

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