本文多资源,建议阅读收藏。
本文列出了一系列包含四个主题的相关资源教程列表,一起来充电学习吧~
[ 导读 ]近年来,机器学习等新最新技术层出不穷,如何跟踪最新的热点以及最新资源,作者Robbie Allen列出了一系列相关资源教程列表,包含四个主题:机器学习,自然语言处理,Python和数学,建议大家收藏学习!
去年我写了一份相当受欢迎的博文(在Medium上有16万阅读量,相关资源1),列出了我在深入研究大量机器学习资源时发现的最佳教程。十三个月后,现在有许多关于传统机器学习概念的新教程大量涌现以及过去一年中出现的新技术。围绕机器学习持续增加的大量内容有着惊人的数量。
本文包含了迄今为止我发现的最好的一些教程内容。它绝不是网上每个ML相关教程的简单详尽列表(这个工作量无疑是十分巨大而又枯燥重复的),而是经过详细筛选后的结果。我的目标就是将我在机器学习和自然语言处理领域各个方面找到的我认为最好的教程整理出来。
在教程中,为了能够更好的让读者理解其中的概念,我将避免罗列书中每章的详细内容,而是总结一些概念性的介绍内容。为什么不直接去买本书?当你想要对某些特定的主题或者不同方面进行了初步了解时,我相信这些教程对你可能帮助更大。
本文中我将分四个主题进行整理: 机器学习,自然语言处理,Python和数学。在每个主题中我将包含一个例子和多个资源。当然我不可能完全覆盖所有的主题啦。
如果你发现我在这里遗漏了好的教程资源,请联系告诉我。为了避免资源重复罗列,我在每个主题下只列出了5、6个教程。下面的每个链接都应该链接了和其他链接不同的资源,也会通过不同的方式(例如幻灯片代码段)或者不同的角度呈现出这些内容。
相关资源
1. 2017版教程资源 Over 150 ofthe Best Machine Learning,NLP,and Python Tutorials I’ve Found(150多个最好的与机器学习,自然语言处理和Python相关的教程)
英文:
中文翻译:
2. My Curated List of AI and Machine LearningResources from Around the Web( 终极收藏AI领域你不能不关注的大牛、机构、课程、会议、图书)
英文:
1989年,Holland的学生D.E.Goldberg出版了专著《搜索、优化和机器学习中的遗传算法》(Genetic Algorithms in Search , Optimization, and Machine Learning)。该书总结了遗传算法研究的主要成果,对遗传算法及其应用作了全面而系统的论述。同年。
中文翻译:
3. Cheat Sheet of Machine Learningand Python (and Math) Cheat Sheets(值得收藏的27 个机器学习的小抄)
英文:
目录
一、机器学习
1.1 激活函数与损失函数
1.2 偏差(bias)
1.3 感知机(perceptron)
企业回地毯多种多样,天匠手工地毯,在欧美,手工地毯界“上门试铺”的销售传统由来已久。天匠曾经在洛杉矶设立了一处全美境内最大的手工真丝地毯仓库,每年都会吸引大量伊朗、土耳其的地毯商人前来选购参观。他们开着之类的厢式货车,每次来都大批量。
1.4 回归(Regression)
1.5 梯度下降(Gradient Descent)
1.6 生成学习(Generative Learning)
1.7 支持向量机(Support Vector Machines)
1.8 反向传播(Backpropagation)
1.9 深度学习(Deep Learning)
1.10 优化与降维(Optimization and Dimensionality Reduction)
1.11 Long Short Term Memory (LSTM)
1.12 卷积神经网络 Convolutional Neural Networks (CNNs)
1.13 循环神经网络 Recurrent Neural Nets (RNNs)
1.14 强化学习 Reinforcement Learning
1.15 生产对抗模型 Generative Adversarial Networks (GANs)
1.16 多任务学习 Multi-task Learning
二、自然语言处理 NLP
2.1 深度学习与自然语言处理 Deep Learning and NLP
2.2 词向量 Word Vectors
2.3 编解码模型 Encoder-Decoder
三、Python
3.1 样例 Examples
3.2 Scipy and numpy教程
3.3 scikit-learn教程
3.4 Tensorflow教程
3.5 PyTorch教程
四、数学基础教程
4.1 线性代数
4.2 概率论
4.3 微积分
一、机器学习
Start Here with MachineLearning (machinelearningmastery.com)
Rules of Machine Learning: BestPractices for ML Engineering(martin.zinkevich.org)
An Introduction to MachineLearning Theory and Its Applications: A Visual Tutorial withExamples (toptal.com)
Which machine learningalgorithm should I use? (sas.com)
Machine Learning Tutorial forBeginners (kaggle.com/kanncaa1)
1.1 激活函数与损失函数
Sigmoidneurons (neuralnetworksanddeeplearning.com)
Comprehensive list ofactivation functions in neural networks with pros/cons(stats.stackexchange.com)
Making Sense of LogarithmicLoss (exegetic.biz)
L1 vs. L2 Lossfunction (rishy.github.io)
The cross-entropy costfunction (neuralnetworksanddeeplearning.com)
1.2 偏差(bias)
Role of Bias in NeuralNetworks (stackoverflow.com)
What is bias in artificialneural network? (quora.com)
1.3 感知机(perceptron)
Perceptrons (neuralnetworksanddeeplearning.com)
Single-layer Neural Networks (Perceptrons) (dcu.ie)
From Perceptrons to DeepNetworks (toptal.com)
1.4 回归(Regression)
Introduction to linearregression analysis (duke.edu)
LinearRegression (readthedocs.io)
Simple Linear RegressionTutorial for Machine Learning (machinelearningmastery.com)
SoftmaxRegression (ufldl.stanford.edu)
1.5 梯度下降(Gradient Descent)
Learning with gradientdescent (neuralnetworksanddeeplearning.com)
How to understand GradientDescent algorithm (kdnuggets.com)
Optimization: StochasticGradient Descent (Stanford CS231n)
1.6 生成学习(Generative Learning)
Generative LearningAlgorithms (Stanford CS229)
A practical explanation of aNaive Bayes classifier (monkeylearn.com)
1.7 支持向量机(Support Vector Machines)
An introduction to SupportVector Machines (SVM) (monkeylearn.com)
Linear classification: SupportVector Machine,Softmax (Stanford 231n)
1.8 反向传播(Backpropagation)
Yes you should understandbackprop (medium.com/@karpathy)
How the backpropagationalgorithm works(neuralnetworksanddeeplearning.com)
out,A Gentle Introduction toBackpropagation Through Time(machinelearningmastery.com)
Backpropagation,Intuitions (Stanford CS231n)
1.9 深度学习(Deep Learning)
A Guide to Deep Learning byYN² (yerevann.com)
Deep Learning in aNutshell (nikhilbuduma.com)
What is DeepLearning? (machinelearningmastery.com)
Deep Learning—TheStraight Dope (gluon.mxnet.io)
50根取出一根不用。(还有49根。然后分为两分,再从着两份中取出一根放在一边。这两分应该总共48根,然后这两份分别除4后的余数。一边为1的话。另一边一定为3,一边为2的话。另一边一定为2,一边无余的话,另一边也。
1.10 优化与降维(Optimization and Dimensionality Reduction)
Seven Techniques for DataDimensionality Reduction (knime.org)
Dropout: A simple way toimprove neural networks (Hinton @ NIPS 2012)
in,How to train your Deep NeuralNetwork (rishy.github.io)
1.11 Long Short Term Memory (LSTM)
A Gentle Introduction to LongShort-Term Memory Networks by the Experts(machinelearningmastery.com)
Exploring LSTMs (echen.me)
Anyone Can Learn To Code anLSTM-RNN in Python (iamtrask.github.io)
1.12 卷积神经网络 Convolutional Neural Networks (CNNs)
Introducing convolutionalnetworks (neuralnetworksanddeeplearning.com)
Conv Nets: A ModularPerspective (colah.github.io)
UnderstandingConvolutions (colah.github.io)
1.13 循环神经网络 Recurrent Neural Nets (RNNs)
Recurrent Neural NetworksTutorial (wildml.com)
The Unreasonable Effectivenessof Recurrent Neural Networks (karpathy.github.io)
and,A Deep Dive into RecurrentNeural Nets (nikhilbuduma.com)
1.14 强化学习 Reinforcement Learning
Simple Beginner’s guide toReinforcement Learning & its implementation(analyticsvidhya.com)
Learning ReinforcementLearning (wildml.com)
Deep Reinforcement Learning:Pong from Pixels (karpathy.github.io)
1.15 生产对抗模型 Generative Adversarial Networks (GANs)
Adversarial MachineLearning (aaai18adversarial.github.io)
Abusing Generative AdversarialNetworks to Make 8-bit Pixel Art(medium.com/@ageitgey)
Generative Adversarial Networksfor Beginners (oreilly.com)
1.16 多任务学习 Multi-task Learning
An Overview of Multi-TaskLearning in Deep Neural Networks (sebastianruder.com)
二、自然语言处理 NLP
Natural Language Processing isFun! (medium.com/@ageitgey)
The Definitive Guide to NaturalLanguage Processing (monkeylearn.com)
Natural Language Processing Tutorial (vikparuchuri.com)
Natural Language Processing(almost) from Scratch (arxiv.org)
2.1 深度学习与自然语言处理 Deep Learning and NLP
Deep Learning applied toNLP (arxiv.org)
Understanding ConvolutionalNeural Networks for NLP (wildml.com)
Embed,encode,attend,predict:The new deep learning formula for state-of-the-art NLPmodels (explosion.ai)
Deep Learning for NLP withPytorch (pytorich.org)
2.2 词向量 Word Vectors
Bag of Words Meets Bags ofPopcorn (kaggle.com)
The amazing power of wordvectors (acolyer.org)
Word2Vec Tutorial—TheSkip-Gram Model,Negative Sampling (mccormickml.com)
2.3 编解码模型 Encoder-Decoder
Attention and Memory in DeepLearning and NLP (wildml.com)
Sequence to Sequence Learningwith Neural Networks (NIPS 2014)
How to use an Encoder-DecoderLSTM to Echo Sequences of Random Integers(machinelearningmastery.com)
7 Steps to Mastering MachineLearning With Python (kdnuggets.com)
Machine Learning withPython (tutorialspoint.com)
3.1 样例 Examples
How To Implement The Perceptron Algorithm From Scratch In Python(machinelearningmastery.com)
A Neural Network in 11 lines ofPython (iamtrask.github.io)
ML fromScatch (github.com/eriklindernoren)
Python Machine Learning (2ndEd.) Code Repository (github.com/rasbt)
3.2 Scipy and numpy教程
Scipy LectureNotes (scipy-lectures.org)
An introduction to Numpy andScipy (UCSB CHE210D)
A Crash Course in Python forScientists (nbviewer.jupyter.org)
3.3 scikit-learn教程
PyCon scikit-learn TutorialIndex (nbviewer.jupyter.org)
scikit-learnTutorials (scikit-learn.org)
of,Abridged scikit-learn Tutorials (github.com/mmmayo13)
3.4 Tensorflow教程
Tensorflow Tutorials (tensorflow.org)
TensorFlow: Aprimer (metaflow.fr)
Implementing a CNN for TextClassification in TensorFlow (wildml.com)
How to Run Text Summarizationwith TensorFlow (surmenok.com)
3.5 PyTorch教程
PyTorchTutorials (pytorch.org)
Tutorial: Deep Learning inPyTorch (iamtrask.github.io)
PyTorchTutorial (github.com/MorvanZhou)
PyTorch Tutorial for DeepLearning Researchers (github.com/yunjey)
四、数学基础教程
空间定义的GA(Genetic Algorithm in Continuous Space, GACS),暂不讨论。一个串行运算的遗传算法(Seguential Genetic Algoritm, SGA)按如下过程进行:(1) 对待解决问题进行编码;(2) 随机初始化群体X(0):=(x1, x
Math for MachineLearning (ucsc.edu)
Goldberg D E.Genetic algorithms in Search Optimization and Machine Learing.MA:Addison-Wesley,1989 Rudolph Gunter.Convergence analysis of canonical genetic algorithms.IEEE Transactions on Neural Networks,1994,5 (1);102~119 Fang。
Math for MachineLearning (UMIACS CMSC422)
4.1 线性代数
Understanding the Cross Product (betterexplained.com)
Linear Algebra for MachineLearning (U. of Buffalo CSE574)
Linear Algebra Review andReference (Stanford CS229)
4.2 概率论
Understanding Bayes TheoremWith Ratios (betterexplained.com)
Probability Theory Review forMachine Learning (Stanford CS229)
Probability Theory for MachineLearning (U. of Toronto CSC411)
4.3 微积分
How To Understand Derivatives:The Quotient Rule,Exponents,and Logarithms (betterexplained.com)
Vector Calculus: Understandingthe Gradient (betterexplained.com)
CalculusOverview (readthedocs.io)