book

Deep Learning with TensorFlow - Second Edition

by Giancarlo Zaccone, Vihan Jain, Md. Rezaul Karim, Motaz Saad

March 2018

Intermediate to advanced

484 pages

10h 31m

English

Packt Publishing

Read now

Unlock full access

Why subscribe?
About the authors
Who this book is for
Download the example code filesDownload the color imagesConventions used

Reviews
A soft introduction to machine learningSupervised learningUnbalanced dataUnsupervised learningReinforcement learningWhat is deep learning?
The biological neuronsThe artificial neuron
ANNs and the backpropagation algorithmWeight optimizationStochastic gradient descent
Deep Neural Networks (DNNs)Multilayer perceptronDeep Belief Networks (DBNs)Convolutional Neural Networks (CNNs)AutoEncodersRecurrent Neural Networks (RNNs)Emergent architectures
A general overview of TensorFlow
Nvidia GPU support optimizedIntroducing TensorFlow LiteEager executionOptimized Accelerated Linear Algebra (XLA)
Eager execution with TensorFlow
TensorRank and shapeData typeVariablesFetchesFeeds and placeholders
How does TensorBoard work?
Linear regression revisited for a real dataset
Feed-forward neural networks (FFNNs)Feed-forward and backpropagationWeights and biasesActivation functionsUsing sigmoidUsing tanhUsing ReLUUsing softmax
Exploring the MNIST datasetSoftmax classifier
Training an MLPUsing MLPsDataset descriptionPreprocessingA TensorFlow implementation of MLP for client-subscription assessmentDeep Belief Networks (DBNs)Restricted Boltzmann Machines (RBMs)Construction of a simple DBNUnsupervised pre-trainingSupervised fine-tuningImplementing a DBN with TensorFlow for client-subscription assessment
Tuning FFNN hyperparametersNumber of hidden layersNumber of neurons per hidden layerWeight and biases initializationSelecting the most suitable optimizerGridSearch and randomized search for hyperparameters tuningRegularizationDropout optimization
Main concepts of CNNs
AlexNetTransfer learningPretrained AlexNet
VGGArtistic style learning with VGG-19Input imagesContent extractor and lossStyle extractor and lossMerger and total lossTraining
Exploring Inception with TensorFlow
Testing the model on your own imageSource code
How does an autoencoder work?
Implementing a denoising autoencoderImplementing a convolutional autoencoderEncoderDecoder
Description of the datasetProblem descriptionExploratory data analysisTraining, validation, and testing set preparationNormalizationAutoencoder as an unsupervised feature learning algorithmEvaluating the model
Working principles of RNNsImplementing basic RNNs in TensorFlowRNN and the long-term dependency problemBi-directional RNNs
LSTM networksGRU cell
Data description and preprocessing
Description of the datasetPre-processing and exploratory analysisLSTM predictive modelModel evaluation
Network designLSTM model trainingVisualizing through TensorBoardLSTM model evaluation
Dataset descriptionWorkflow of the LSTM model for HARImplementing an LSTM model for HAR
GPGPU computingThe GPGPU historyThe CUDA architectureThe GPU programming model
Update TensorFlowGPU representationUsing a GPUGPU memory managementAssigning a single GPU on a multi-GPU systemThe source code for GPU with soft placementUsing multiple GPUs
Model parallelismData parallelism
tf.estimatorEstimatorsGraph actionsParsing resourcesFlower predictions
InstallationTitanic survival predictor
Chaining layersNormal modeSequential modeBranch and joinDigit classifier
Keras programming modelsSequential modelSentiment classification of movie reviewsFunctional APISqueezeNet
Recommendation systemsCollaborative filtering approachesContent-based filtering approachesHybrid recommender systemsModel-based collaborative filtering
The utility matrixDescription of the datasetRatings dataMovies dataUsers dataExploratory analysis of the MovieLens datasetImplementing a movie RETraining the model with the available ratingsInferencing the saved modelGenerating the user-item tableClustering similar moviesMovie rating prediction by usersFinding top k moviesPredicting top k similar moviesComputing user-user similarityEvaluating the recommender system
Factorization machinesCold-start problem and collaborative-filtering approachesProblem definition and formulationDataset descriptionWorkflow of the implementationPreprocessingTraining the FM model
Neural factorization machinesDataset descriptionUsing NFM for the movie recommendationModel trainingModel evaluation
The RL problem
OpenAI environmentsThe env classInstalling and running OpenAI Gym
The FrozenLake environment
Deep Q neural networksThe Cart-Pole problemDeep Q-Network for the Cart-Pole problemThe Experience Replay methodExploitation and explorationThe Deep Q-Learning training algorithm
Leave a review – let other readers know what you think

Content preview from Deep Learning with TensorFlow - Second Edition

Summary

In this chapter, we had a quick look at two fundamentals topics related to optimizing the computation of DNNs.

The first topic explained how to use GPUs and TensorFlow to implement DNNs. They are structured in a very uniform manner so that, at each layer of the network, thousands of identical artificial neurons perform the same computation. Hence, the architecture of a DNN fits quite well with the kinds of computation that a GPU can efficiently perform.

The second topic introduced distributed computing. This was initially used to perform very complex calculations that could not be completed by a single machine. Likewise, analyzing large amounts of data quickly by splitting this task among different nodes appears to be the best strategy when ...