没有合适的资源?快使用搜索试试~ 我知道了~
首页Deep Learning with TensorFlow第二版pdf
Deep Learning with TensorFlow第二版pdf

Apply deep machine intelligence and GPU computing with TensorFlow v1.7 Access public datasets and use TensorFlow to load, process, and transform the data Discover how to use the high-level TensorFlow API to build more powerful applications Use deep learning for scalable object detection and mobile computing Train machines quickly to learn from data by exploring reinforcement learning techniques Explore active areas of deep learning research and applications
资源详情
资源评论
资源推荐


TableofContents
DeepLearningwithTensorFlow-SecondEdition
Whysubscribe?
PacktPub.com
Contributors
Abouttheauthors
Aboutthereviewers
PacktisSearchingforAuthorsLikeYou
Preface
Whothisbookisfor
Whatthisbookcovers
Togetthemostoutofthisbook
Downloadtheexamplecodefiles
Downloadthecolorimages
Conventionsused
Getintouch
Reviews
1.GettingStartedwithDeepLearning
Asoftintroductiontomachinelearning
Supervisedlearning
Unbalanceddata
Unsupervisedlearning
Reinforcementlearning
Whatisdeeplearning?
Artificialneuralnetworks
Thebiologicalneurons
Theartificialneuron
HowdoesanANNlearn?
ANNsandthebackpropagationalgorithm
Weightoptimization
Stochasticgradientdescent
Neuralnetworkarchitectures
DeepNeuralNetworks(DNNs)
Multilayerperceptron
DeepBeliefNetworks(DBNs)
ConvolutionalNeuralNetworks(CNNs)
AutoEncoders
RecurrentNeuralNetworks(RNNs)
Emergentarchitectures
Deeplearningframeworks
Summary
2.AFirstLookatTensorFlow
AgeneraloverviewofTensorFlow
What'snewfromTensorFlowv1.6forwards?
NvidiaGPUsupportoptimized
IntroducingTensorFlowLite
2

Eagerexecution
OptimizedAcceleratedLinearAlgebra(XLA)
InstallingandconfiguringTensorFlow
TensorFlowcomputationalgraph
TensorFlowcodestructure
EagerexecutionwithTensorFlow
DatamodelinTensorFlow
Tensor
Rankandshape
Datatype
Variables
Fetches
Feedsandplaceholders
VisualizingcomputationsthroughTensorBoard
HowdoesTensorBoardwork?
Linearregressionandbeyond
Linearregressionrevisitedforarealdataset
Summary
3.Feed-ForwardNeuralNetworkswithTensorFlow
Feed-forwardneuralnetworks(FFNNs)
Feed-forwardandbackpropagation
Weightsandbiases
Activationfunctions
Usingsigmoid
Usingtanh
UsingReLU
Usingsoftmax
Implementingafeed-forwardneuralnetwork
ExploringtheMNISTdataset
Softmaxclassifier
Implementingamultilayerperceptron(MLP)
TraininganMLP
UsingMLPs
Datasetdescription
Preprocessing
ATensorFlowimplementationofMLPforclient-subscriptionassessment
DeepBeliefNetworks(DBNs)
RestrictedBoltzmannMachines(RBMs)
ConstructionofasimpleDBN
Unsupervisedpre-training
Supervisedfine-tuning
ImplementingaDBNwithTensorFlowforclient-subscriptionassessment
TuninghyperparametersandadvancedFFNNs
TuningFFNNhyperparameters
Numberofhiddenlayers
Numberofneuronsperhiddenlayer
Weightandbiasesinitialization
Selectingthemostsuitableoptimizer
GridSearchandrandomizedsearchforhyperparameterstuning
3

Regularization
Dropoutoptimization
Summary
4.ConvolutionalNeuralNetworks
MainconceptsofCNNs
CNNsinaction
LeNet5
ImplementingaLeNet-5stepbystep
AlexNet
Transferlearning
PretrainedAlexNet
Datasetpreparation
Fine-tuningimplementation
VGG
ArtisticstylelearningwithVGG-19
Inputimages
Contentextractorandloss
Styleextractorandloss
Mergerandtotalloss
Training
Inception-v3
ExploringInceptionwithTensorFlow
EmotionrecognitionwithCNNs
Testingthemodelonyourownimage
Sourcecode
Summary
5.OptimizingTensorFlowAutoencoders
Howdoesanautoencoderwork?
ImplementingautoencoderswithTensorFlow
Improvingautoencoderrobustness
Implementingadenoisingautoencoder
Implementingaconvolutionalautoencoder
Encoder
Decoder
Fraudanalyticswithautoencoders
Descriptionofthedataset
Problemdescription
Exploratorydataanalysis
Training,validation,andtestingsetpreparation
Normalization
Autoencoderasanunsupervisedfeaturelearningalgorithm
Evaluatingthemodel
Summary
6.RecurrentNeuralNetworks
WorkingprinciplesofRNNs
ImplementingbasicRNNsinTensorFlow
RNNandthelong-termdependencyproblem
Bi-directionalRNNs
RNNandthegradientvanishing-explodingproblem
4

LSTMnetworks
GRUcell
ImplementinganRNNforspamprediction
Datadescriptionandpreprocessing
Developingapredictivemodelfortimeseriesdata
Descriptionofthedataset
Pre-processingandexploratoryanalysis
LSTMpredictivemodel
Modelevaluation
AnLSTMpredictivemodelforsentimentanalysis
Networkdesign
LSTMmodeltraining
VisualizingthroughTensorBoard
LSTMmodelevaluation
HumanactivityrecognitionusingLSTMmodel
Datasetdescription
WorkflowoftheLSTMmodelforHAR
ImplementinganLSTMmodelforHAR
Summary
7.HeterogeneousandDistributedComputing
GPGPUcomputing
TheGPGPUhistory
TheCUDAarchitecture
TheGPUprogrammingmodel
TheTensorFlowGPUsetup
UpdateTensorFlow
GPUrepresentation
UsingaGPU
GPUmemorymanagement
AssigningasingleGPUonamulti-GPUsystem
ThesourcecodeforGPUwithsoftplacement
UsingmultipleGPUs
Distributedcomputing
Modelparallelism
Dataparallelism
ThedistributedTensorFlowsetup
Summary
8.AdvancedTensorFlowProgramming
tf.estimator
Estimators
Graphactions
Parsingresources
Flowerpredictions
TFLearn
Installation
Titanicsurvivalpredictor
PrettyTensor
Chaininglayers
Normalmode
5
剩余444页未读,继续阅读
















安全验证
文档复制为VIP权益,开通VIP直接复制

评论3