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RobbieAllen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。
相关资源作者RobbieAllen是以为科技作者和创业者、并自学AI并成为博士生。曾整理许多广为流传的机器学习相关资源。
1.2017版教程资源Over150oftheBestMachineLearning,NLP,andPythonTutorialsI’veFound(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:
英文:
中文翻译:
3.CheatSheetofMachineLearningandPython(andMath)CheatSheets(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)
1.4回归(Regression)
1.5梯度下降(GradientDescent)
1.6生成学习(GenerativeLearning)
1.7支持向量机(SupportVectorMachines)
1.8反向传播(Backpropagation)
1.9深度学习(DeepLearning)
1.10优化与降维(OptimizationandDimensionalityReduction)
1.11LongShortTermMemory(LSTM)
1.12卷积神经网络ConvolutionalNeuralNetworks(CNNs)
1.13循环神经网络RecurrentNeuralNets(RNNs)
1.14强化学习ReinforcementLearning
1.15生产对抗模型GenerativeAdversarialNetworks(GANs)
1.16多任务学习Multi-taskLearning
二、自然语言处理NLP
2.1深度学习与自然语言处理DeepLearningandNLP
2.2词向量WordVectors
2.3编解码模型Encoder-Decoder
三、Python
3.1样例Examples
3.2Scipyandnumpy教程
3.3scikit-learn教程
3.4Tensorflow教程
3.5PyTorch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StartHerewithMachineLearning()
MachineLearningisFun!(/@ageitgey)
RulesofMachineLearning:BestPracticesforMLEngineering()
MachineLearningCrashCourse:PartI,PartII,PartIII(MachineLearningatBerkeley)
PartI
PartII
PartIII
AnIntroductiontoMachineLearningTheoryandItsApplications:AVisualTutorialwithExamples()
AGentleGuidetoMachineLearning()
WhichmachinelearningalgorithmshouldIuse?()
TheMachineLearningPrimer()
MachineLearningTutorialforBeginners(/kanncaa1)
1.1激活函数与损失函数
Sigmoidneurons()
Whatistheroleoftheactivationfunctioninaneuralnetwork?()
Comprehensivelistofactivationfunctionsinneuralnetworkswithpros/cons()
Activationfunctionsandit’stypes-Whichisbetter?()
MakingSenseofLogarithmicLoss()
LossFunctions(StanfordCS231n)
()
Thecross-entropycostfunction()
1.2偏差(bias)
RoleofBiasinNeuralNetworks()
BiasNodesinNeuralNetworks()
Whatisbiasinartificialneuralnetwork?()
1.3感知机(perceptron)
Perceptrons()
ThePerception()
Single-layerNeuralNetworks(Perceptrons)()
FromPerceptronstoDeepNetworks()
1.4回归(Regression)
Introductiontolinearregressionanalysis()
LinearRegression()
LinearRegression()
LogisticRegression()
SimpleLinearRegressionTutorialforMachineLearning()
LogisticRegressionTutorialforMachineLearning()
SoftmaxRegression()
1.5梯度下降(GradientDescent)
Learningwithgradientdescent()
GradientDescent()
HowtounderstandGradientDescentalgorithm()
Anoverviewofgradientdescentoptimizationalgorithms()
Optimization:StochasticGradientDescent(StanfordCS231n)
1.6生成学习(GenerativeLearning)
GenerativeLearningAlgorithms(StanfordCS229)
ApracticalexplanationofaNaiveBayesclassifier()
1.7支持向量机(SupportVectorMachines)
AnintroductiontoSupportVectorMachines(SVM)()
SupportVectorMachines(StanfordCS229)
Linearclassification:SupportVectorMachine,Softmax(Stanford231n)
1.8反向传播(Backpropagation)
Yesyoushouldunderstandbackprop(/@karpathy)
Canyougiveavisualexplanationforthebackpropagationalgorithmforneuralnetworks?(/rasbt)
Howthebackpropagationalgorithmworks()
BackpropagationThroughTimeandVanishingGradients()
AGentleIntroductiontoBackpropagationThroughTime()
Backpropagation,Intuitions(StanfordCS231n)
1.9深度学习(DeepLearning)
AGuidetoDeepLearningbyYN²()
DeepLearningPapersReadingRoadmap(/floodsung)
DeepLearninginaNutshell()
ATutorialonDeepLearning()
WhatisDeepLearning?()
What’stheDifferenceBetweenArtificialIntelligence,MachineLearning,andDeepLearning?()
DeepLearning—TheStraightDope()
1.10优化与降维(OptimizationandDimensionalityReduction)
SevenTechniquesforDataDimensionalityReduction()
Principalcomponentsanalysis(StanfordCS229)
Dropout:Asimplewaytoimproveneuralnetworks(Hinton@NIPS2012)
HowtotrainyourDeepNeuralNetwork()
1.11LongShortTermMemory(LSTM)
AGentleIntroductiontoLongShort-TermMemoryNetworksbytheExperts()
UnderstandingLSTMNetworks()
ExploringLSTMs()
AnyoneCanLearnToCodeanLSTM-RNNinPython()
1.12卷积神经网络ConvolutionalNeuralNetworks(CNNs)
Introducingconvolutionalnetworks()
DeepLearningandConvolutionalNeuralNetworks(/@ageitgey)
ConvNets:AModularPerspective()
UnderstandingConvolutions()
1.13循环神经网络RecurrentNeuralNets(RNNs)
RecurrentNeuralNetworksTutorial()
AttentionandAugmentedRecurrentNeuralNetworks()
TheUnreasonableEffectivenessofRecurrentNeuralNetworks()
ADeepDiveintoRecurrentNeuralNets()
1.14强化学习ReinforcementLearning
SimpleBeginner’sguidetoReinforcementLearningitsimplementation()
ATutorialforReinforcementLearning()
LearningReinforcementLearning()
DeepReinforcementLearning:PongfromPixels()
1.15生产对抗模型GenerativeAdversarialNetworks(GANs)
AdversarialMachineLearning()
What’saGenerativeAdversarialNetwork?()
AbusingGenerativeAdversarialNetworkstoMake8-bitPixelArt(/@ageitgey)
AnintroductiontoGenerativeAdversarialNetworks(withcodeinTensorFlow)()
GenerativeAdversarialNetworksforBeginners()
1.16多任务学习Multi-taskLearning
AnOverviewofMulti-TaskLearninginDeepNeuralNetworks()
二、自然语言处理NLPNaturalLanguageProcessingisFun!(/@ageitgey)
APrimeronNeuralNetworkModelsforNaturalLanguageProcessing(YoavGoldberg)
TheDefinitiveGuidetoNaturalLanguageProcessing()
IntroductiontoNaturalLanguageProcessing()
NaturalLanguageProcessingTutorial()
NaturalLanguageProcessing(almost)fromScratch()
2.1深度学习与自然语言处理DeepLearningandNLP
DeepLearningappliedtoNLP()
DeepLearningforNLP(withoutMagic)(RichardSocher)
UnderstandingConvolutionalNeuralNetworksforNLP()
DeepLearning,NLP,andRepresentations()
Embed,encode,att,predict:Thenewdeeplearningformulaforstate-of-the-artNLPmodels()
UnderstandingNaturalLanguagewithDeepNeuralNetworksUsingTorch()
DeepLearningforNLPwithPytorch()
2.2词向量WordVectors
BagofWordsMeetsBagsofPopcorn()
OnwordembeddingsPartI,PartII,PartIII()
PartI:
PartII:
PartIII:
Theamazingpowerofwordvectors()
word2vecParameterLearningExplained()
Word2VecTutorial—TheSkip-GramModel,NegativeSampling()
2.3编解码模型Encoder-Decoder
AttentionandMemoryinDeepLearningandNLP()
SequencetoSequenceModels()
SequencetoSequenceLearningwithNeuralNetworks(NIPS2014)
MachineLearningisFunPart5:LanguageTranslationwithDeepLearningandtheMagicofSequences(/@ageitgey)
HowtouseanEncoder-DecoderLSTMtoEchoSequencesofRandomIntegers()
tf-seq2seq()
三、PythonMachineLearningCrashCourse()
AwesomeMachineLearning(/josephmisiti)
7StepstoMasteringMachineLearningWithPython()
Anexamplemachinelearningnotebook()
MachineLearningwithPython()
3.1样例Examples
HowToImplementThePerceptronAlgorithmFromScratchInPython()
ImplementingaNeuralNetworkfromScratchinPython()
ANeuralNetworkin11linesofPython()
ImplementingYourOwnk-NearestNeighbourAlgorithmUsingPython()
MLfromScatch(/eriklindernoren)
PythonMachineLearning(2ndEd.)CodeRepository(/rasbt)
3.2Scipyandnumpy教程
ScipyLectureNotes()
PythonNumpyTutorial(StanfordCS231n)
AnintroductiontoNumpyandScipy(UCSBCHE210D)
ACrashCourseinPythonforScientists()
3.3scikit-learn教程
PyConscikit-learnTutorialIndex()
scikit-learnClassificationAlgorithms(/mmmayo13)
scikit-learnTutorials()
Abridgedscikit-learnTutorials(/mmmayo13)
3.4Tensorflow教程
TensorflowTutorials()
IntroductiontoTensorFlow—CPUvsGPU(/@erikhallstrm)
TensorFlow:Aprimer()
RNNsinTensorflow()
ImplementingaCNNforTextClassificationinTensorFlow()
HowtoRunTextSummarizationwithTensorFlow()
3.5PyTorch教程
PyTorchTutorials()
AGentleIntrotoPyTorch()
Tutorial:DeepLearninginPyTorch()
PyTorchExamples(/jcjohnson)
PyTorchTutorial(/MorvanZhou)
PyTorchTutorialforDeepLearningResearchers(/yunjey)
四、数学基础教程
MathforMachineLearning()
MathforMachineLearning(UMIACSCMSC422)
4.1线性代数
AnIntuitiveGuidetoLinearAlgebra()
AProgrammer’sIntuitionforMatrixMultiplication()
UnderstandingtheCrossProduct()
UnderstandingtheDotProduct()
LinearAlgebraforMachineLearning()
Linearalgebracheatsheetfordeeplearning()
LinearAlgebraReviewandReference(StanfordCS229)
4.2概率论
UnderstandingBayesTheoremWithRatios()
ReviewofProbabilityTheory(StanfordCS229)
ProbabilityTheoryReviewforMachineLearning(StanfordCS229)
ProbabilityTheory()
ProbabilityTheoryforMachineLearning()
4.3微积分
HowToUnderstandDerivatives:TheQuotientRule,Exponents,andLogarithms()
HowToUnderstandDerivatives:TheProduct,PowerChainRules()
VectorCalculus:UnderstandingtheGradient()
DifferentialCalculus(StanfordCS224n)
CalculusOverview()
免责声明:本文章如果文章侵权,请联系我们处理,本站仅提供信息存储空间服务如因作品内容、版权和其他问题请于本站联系