教程推薦 | 機器學習、Python等最好的150餘個教程

來自專欄從零學AI

儘管機器學習的歷史可以追溯到1959年，但目前，這個領域正以前所未有的速度發展。最近，我一直在網上尋找關於機器學習和NLP各方面的好資源，為了幫助到和我有相同需求的人，我整理了一份迄今為止我發現的最好的教程內容列表。

通過教程中的簡介內容講述一個概念。避免了包括書籍章節涵蓋範圍廣，以及研究論文在教學理念上做的不好的特點。

我把這篇文章分成四個部分：機器學習、NLP、Python和數學。每個部分中都包含了一些主題文章，但是由於材料巨大，每個部分不可能包含所有可能的主題，我將每個主題限制在5到6個教程中。

機器學習

• Machine Learning is Fun! (http://medium.com/@ageitgey)
• Machine Learning Crash Course: Part I, Part II, Part III (Machine Learning at Berkeley)
• An Introduction to Machine Learning Theory and Its Applications: A Visual Tutorial with Examples (http://toptal.com)
• A Gentle Guide to Machine Learning (http://monkeylearn.com)
• Which machine learning algorithm should I use? (http://sas.com)

激活和損失函數

• Sigmoid neurons (http://neuralnetworksanddeeplearning.com)
• What is the role of the activation function in a neural network? (http://quora.com)
• Comprehensive list of activation functions in neural networks with pros/cons(http://stats.stackexchange.com)
• Activation functions and it』s types-Which is better? (http://medium.com)
• Making Sense of Logarithmic Loss (http://exegetic.biz)
• Loss Functions (Stanford CS231n)
• L1 vs. L2 Loss function (http://rishy.github.io)
• The cross-entropy cost function (http://neuralnetworksanddeeplearning.com)

Bias

• Role of Bias in Neural Networks (http://stackoverflow.com)
• Bias Nodes in Neural Networks (http://makeyourownneuralnetwork.blogspot.com)
• What is bias in artificial neural network? (http://quora.com)

感知器

• Perceptrons (http://neuralnetworksanddeeplearning.com)
• The Perception (http://natureofcode.com)
• Single-layer Neural Networks (Perceptrons) (dcu.ie)
• From Perceptrons to Deep Networks (http://toptal.com)

回歸

• Introduction to linear regression analysis (http://duke.edu)
• Linear Regression (http://ufldl.stanford.edu)
• Linear Regression (http://readthedocs.io)
• Logistic Regression (http://readthedocs.io)
• Simple Linear Regression Tutorial for Machine Learning(http://machinelearningmastery.com)
• Logistic Regression Tutorial for Machine Learning(http://machinelearningmastery.com)
• Softmax Regression (http://ufldl.stanford.edu)

梯度下降演算法

• Learning with gradient descent (http://neuralnetworksanddeeplearning.com)
• Gradient Descent (http://iamtrask.github.io)
• How to understand Gradient Descent algorithm (http://kdnuggets.com)
• An overview of gradient descent optimization algorithms(http://sebastianruder.com)
• Optimization: Stochastic Gradient Descent (Stanford CS231n)

生成式學習

• Generative Learning Algorithms (Stanford CS229)
• A practical explanation of a Naive Bayes classifier (http://monkeylearn.com)

支持向量機

• An introduction to Support Vector Machines (SVM) (http://monkeylearn.com)
• Support Vector Machines (Stanford CS229)
• Linear classification: Support Vector Machine, Softmax (Stanford 231n)

反向傳播

• Yes you should understand backprop (http://medium.com/@karpathy)
• Can you give a visual explanation for the back propagation algorithm for neural - networks? (http://github.com/rasbt)
• How the backpropagation algorithm works(http://neuralnetworksanddeeplearning.com)
• Backpropagation Through Time and Vanishing Gradients (http://wildml.com)
• A Gentle Introduction to Backpropagation Through Time(http://machinelearningmastery.com)
• Backpropagation, Intuitions (Stanford CS231n)

深度學習

• Deep Learning in a Nutshell (http://nikhilbuduma.com)
• A Tutorial on Deep Learning (Quoc V. Le)
• What is Deep Learning? (http://machinelearningmastery.com)
• What』s the Difference Between Artificial Intelligence, Machine Learning, and Deep - Learning? (http://nvidia.com)

優化和降維

• Seven Techniques for Data Dimensionality Reduction (http://knime.org)
• Principal components analysis (Stanford CS229)
• Dropout: A simple way to improve neural networks (Hinton @ NIPS 2012)
• How to train your Deep Neural Network (http://rishy.github.io)

長短期記憶網路

• A Gentle Introduction to Long Short-Term Memory Networks by the Experts(http://machinelearningmastery.com)
• Understanding LSTM Networks (http://colah.github.io)
• Exploring LSTMs (http://echen.me)
• Anyone Can Learn To Code an LSTM-RNN in Python (http://iamtrask.github.io)

卷積神經網路

• Introducing convolutional networks (http://neuralnetworksanddeeplearning.com)
• Deep Learning and Convolutional Neural Networks(http://medium.com/@ageitgey)
• Conv Nets: A Modular Perspective (http://colah.github.io)
• Understanding Convolutions (http://colah.github.io)

遞歸神經網路

• Recurrent Neural Networks Tutorial (http://wildml.com)
• Attention and Augmented Recurrent Neural Networks (distill.pub)
• The Unreasonable Effectiveness of Recurrent Neural Networks(http://karpathy.github.io)
• A Deep Dive into Recurrent Neural Nets (http://nikhilbuduma.com)

強化學習

• Simple Beginner』s guide to Reinforcement Learning & its implementation(http://analyticsvidhya.com)
• A Tutorial for Reinforcement Learning (http://mst.edu)
• Learning Reinforcement Learning (http://wildml.com)
• Deep Reinforcement Learning: Pong from Pixels (http://karpathy.github.io)

生成對抗網路

• What』s a Generative Adversarial Network? (http://nvidia.com)
• Abusing Generative Adversarial Networks to Make 8-bit Pixel Art(http://medium.com/@ageitgey)
• An introduction to Generative Adversarial Networks (with code in - TensorFlow) (http://aylien.com)
• Generative Adversarial Networks for Beginners (http://oreilly.com)

多任務學習

• An Overview of Multi-Task Learning in Deep Neural Networks(http://sebastianruder.com)

自然語言處理

• A Primer on Neural Network Models for Natural Language Processing (Yoav Goldberg)
• The Definitive Guide to Natural Language Processing (http://monkeylearn.com)
• Introduction to Natural Language Processing (http://algorithmia.com)
• Natural Language Processing Tutorial (http://vikparuchuri.com)
• Natural Language Processing (almost) from Scratch (http://arxiv.org)

深入學習和NLP

• Deep Learning applied to NLP (http://arxiv.org)
• Deep Learning for NLP (without Magic) (Richard Socher)
• Understanding Convolutional Neural Networks for NLP (http://wildml.com)
• Deep Learning, NLP, and Representations (http://colah.github.io)
• Embed, encode, attend, predict: The new deep learning formula for state-of-the-art NLP models (explosion.ai)
• Understanding Natural Language with Deep Neural Networks Using Torch(http://nvidia.com)
• Deep Learning for NLP with Pytorch (http://pytorich.org)

詞向量

• Bag of Words Meets Bags of Popcorn (http://kaggle.com)
• On word embeddings Part I, Part II, Part III (http://sebastianruder.com)
• The amazing power of word vectors (http://acolyer.org)
• word2vec Parameter Learning Explained (http://arxiv.org)
• Word2Vec Tutorial?—?The Skip-Gram Model, Negative Sampling(http://mccormickml.com)

Encoder-Decoder

• Attention and Memory in Deep Learning and NLP (http://wildml.com)
• Sequence to Sequence Models (http://tensorflow.org)
• Sequence to Sequence Learning with Neural Networks (NIPS 2014)
• Machine Learning is Fun Part 5: Language Translation with Deep Learning and the Magic of Sequences (http://medium.com/@ageitgey)
• How to use an Encoder-Decoder LSTM to Echo Sequences of Random Integers(http://machinelearningmastery.com)
• tf-seq2seq (http://google.github.io)

Python

• 7 Steps to Mastering Machine Learning With Python (http://kdnuggets.com)
• An example machine learning notebook (http://nbviewer.jupyter.org)

例子

• How To Implement The Perceptron Algorithm From Scratch In Python(http://machinelearningmastery.com)
• Implementing a Neural Network from Scratch in Python (http://wildml.com)
• A Neural Network in 11 lines of Python (http://iamtrask.github.io)
• Implementing Your Own k-Nearest Neighbour Algorithm Using Python(http://kdnuggets.com)
  Demonstration of Memory with a Long Short-Term Memory Network in - Python (http://machinelearningmastery.com)
• How to Learn to Echo Random Integers with Long Short-Term Memory Recurrent Neural Networks (http://machinelearningmastery.com)
• How to Learn to Add Numbers with seq2seq Recurrent Neural Networks(http://machinelearningmastery.com)

Scipy和numpy

• Scipy Lecture Notes (http://scipy-lectures.org)
• Python Numpy Tutorial (Stanford CS231n)
• An introduction to Numpy and Scipy (UCSB CHE210D)
• A Crash Course in Python for Scientists (http://nbviewer.jupyter.org)

scikit-learn

• PyCon scikit-learn Tutorial Index (http://nbviewer.jupyter.org)
• scikit-learn Classification Algorithms (http://github.com/mmmayo13)
• scikit-learn Tutorials (http://scikit-learn.org)
• Abridged scikit-learn Tutorials (http://github.com/mmmayo13)

Tensorflow

• Tensorflow Tutorials (http://tensorflow.org)
• Introduction to TensorFlow?—?CPU vs GPU (http://medium.com/@erikhallstrm)
• TensorFlow: A primer (http://metaflow.fr)
• RNNs in Tensorflow (http://wildml.com)
• Implementing a CNN for Text Classification in TensorFlow (http://wildml.com)
• How to Run Text Summarization with TensorFlow (http://surmenok.com)

PyTorch

• PyTorch Tutorials (http://pytorch.org)
• A Gentle Intro to PyTorch (http://gaurav.im)
• Tutorial: Deep Learning in PyTorch (http://iamtrask.github.io)
• PyTorch Examples (http://github.com/jcjohnson)
• PyTorch Tutorial (http://github.com/MorvanZhou)
• PyTorch Tutorial for Deep Learning Researchers (http://github.com/yunjey)

數學

• Math for Machine Learning (http://ucsc.edu)
• Math for Machine Learning (UMIACS CMSC422)

線性代數

• An Intuitive Guide to Linear Algebra (http://betterexplained.com)
• A Programmer』s Intuition for Matrix Multiplication (http://betterexplained.com)
• Understanding the Cross Product (http://betterexplained.com)
• Understanding the Dot Product (http://betterexplained.com)
• Linear Algebra for Machine Learning (U. of Buffalo CSE574)
• Linear algebra cheat sheet for deep learning (http://medium.com)
• Linear Algebra Review and Reference (Stanford CS229)

概率

• Understanding Bayes Theorem With Ratios (http://betterexplained.com)
• Review of Probability Theory (Stanford CS229)
• Probability Theory Review for Machine Learning (Stanford CS229)
• Probability Theory (U. of Buffalo CSE574)
• Probability Theory for Machine Learning (U. of Toronto CSC411)

微積分

• How To Understand Derivatives: The Quotient Rule, Exponents, and Logarithms (http://betterexplained.com)
• How To Understand Derivatives: The Product, Power & Chain Rules(http://betterexplained.com)
• Vector Calculus: Understanding the Gradient (http://betterexplained.com)
• Differential Calculus (Stanford CS224n)
• Calculus Overview (http://readthedocs.io)

原文鏈接https://unsupervisedmethods.com/over-150-of-the-best-machine-learning-nlp-and-python-tutorials-ive-found-ffce2939bd78

《機器學習 第九期》從零到機器學習實戰項目，提供GPU&CPU雙雲平台，作業考試1V1批改（優秀學員內推BAT等）；點擊文末「閱讀原文」了解詳情

http://weixin.qq.com/r/NDjo8E3EtRDKrQmT920m (二維碼自動識別)

推薦閱讀：