book

Fundamentals of Deep Learning

by Nikhil Buduma

June 2017

Intermediate to advanced

296 pages

8h 23m

English

O'Reilly Media, Inc.

Read now

Unlock full access

Prerequisites and ObjectivesConventions Used in This BookUsing Code ExamplesSafari® Books OnlineHow to Contact UsAcknowledgements
Building Intelligent MachinesThe Limits of Traditional Computer ProgramsThe Mechanics of Machine LearningThe NeuronExpressing Linear Perceptrons as NeuronsFeed-Forward Neural NetworksLinear Neurons and Their LimitationsSigmoid, Tanh, and ReLU NeuronsSoftmax Output LayersLooking Forward
The Fast-Food ProblemGradient DescentThe Delta Rule and Learning RatesGradient Descent with Sigmoidal NeuronsThe Backpropagation AlgorithmStochastic and Minibatch Gradient DescentTest Sets, Validation Sets, and OverfittingPreventing Overfitting in Deep Neural NetworksSummary
What Is TensorFlow?How Does TensorFlow Compare to Alternatives?Installing TensorFlowCreating and Manipulating TensorFlow VariablesTensorFlow OperationsPlaceholder TensorsSessions in TensorFlowNavigating Variable Scopes and Sharing VariablesManaging Models over the CPU and GPUSpecifying the Logistic Regression Model in TensorFlowLogging and Training the Logistic Regression ModelLeveraging TensorBoard to Visualize Computation Graphs and LearningBuilding a Multilayer Model for MNIST in TensorFlowSummary
The Challenges with Gradient DescentLocal Minima in the Error Surfaces of Deep NetworksModel IdentifiabilityHow Pesky Are Spurious Local Minima in Deep Networks?Flat Regions in the Error SurfaceWhen the Gradient Points in the Wrong DirectionMomentum-Based OptimizationA Brief View of Second-Order MethodsLearning Rate AdaptationAdaGrad—Accumulating Historical GradientsRMSProp—Exponentially Weighted Moving Average of GradientsAdam—Combining Momentum and RMSPropThe Philosophy Behind Optimizer SelectionSummary
Neurons in Human VisionThe Shortcomings of Feature SelectionVanilla Deep Neural Networks Don’t ScaleFilters and Feature MapsFull Description of the Convolutional LayerMax PoolingFull Architectural Description of Convolution NetworksClosing the Loop on MNIST with Convolutional NetworksImage Preprocessing Pipelines Enable More Robust ModelsAccelerating Training with Batch NormalizationBuilding a Convolutional Network for CIFAR-10Visualizing Learning in Convolutional NetworksLeveraging Convolutional Filters to Replicate Artistic StylesLearning Convolutional Filters for Other Problem DomainsSummary
Learning Lower-Dimensional RepresentationsPrincipal Component AnalysisMotivating the Autoencoder ArchitectureImplementing an Autoencoder in TensorFlowDenoising to Force Robust RepresentationsSparsity in AutoencodersWhen Context Is More Informative than the Input VectorThe Word2Vec FrameworkImplementing the Skip-Gram ArchitectureSummary
Analyzing Variable-Length InputsTackling seq2seq with Neural N-GramsImplementing a Part-of-Speech TaggerDependency Parsing and SyntaxNetBeam Search and Global NormalizationA Case for Stateful Deep Learning ModelsRecurrent Neural NetworksThe Challenges with Vanishing GradientsLong Short-Term Memory (LSTM) UnitsTensorFlow Primitives for RNN ModelsImplementing a Sentiment Analysis ModelSolving seq2seq Tasks with Recurrent Neural NetworksAugmenting Recurrent Networks with AttentionDissecting a Neural Translation NetworkSummary
Neural Turing MachinesAttention-Based Memory AccessNTM Memory Addressing MechanismsDifferentiable Neural ComputersInterference-Free Writing in DNCsDNC Memory ReuseTemporal Linking of DNC WritesUnderstanding the DNC Read HeadThe DNC Controller NetworkVisualizing the DNC in ActionImplementing the DNC in TensorFlowTeaching a DNC to Read and ComprehendSummary
Deep Reinforcement Learning Masters Atari GamesWhat Is Reinforcement Learning?Markov Decision Processes (MDP)PolicyFuture ReturnDiscounted Future ReturnExplore Versus ExploitPolicy Versus Value LearningPolicy Learning via Policy GradientsPole-Cart with Policy GradientsOpenAI GymCreating an AgentBuilding the Model and OptimizerSampling ActionsKeeping Track of HistoryPolicy Gradient Main FunctionPGAgent Performance on Pole-CartQ-Learning and Deep Q-NetworksThe Bellman EquationIssues with Value IterationApproximating the Q-FunctionDeep Q-Network (DQN)Training DQNLearning StabilityTarget Q-NetworkExperience ReplayFrom Q-Function to PolicyDQN and the Markov AssumptionDQN’s Solution to the Markov AssumptionPlaying Breakout wth DQNBuilding Our ArchitectureStacking FramesSetting Up Training OperationsUpdating Our Target Q-NetworkImplementing Experience ReplayDQN Main LoopDQNAgent Results on BreakoutImproving and Moving Beyond DQNDeep Recurrent Q-Networks (DRQN)Asynchronous Advantage Actor-Critic Agent (A3C)UNsupervised REinforcement and Auxiliary Learning (UNREAL)Summary

Overview

With the reinvigoration of neural networks in the 2000s, deep learning has become an extremely active area of research, one that’s paving the way for modern machine learning. In this practical book, author Nikhil Buduma provides examples and clear explanations to guide you through major concepts of this complicated field.

Companies such as Google, Microsoft, and Facebook are actively growing in-house deep-learning teams. For the rest of us, however, deep learning is still a pretty complex and difficult subject to grasp. If you’re familiar with Python, and have a background in calculus, along with a basic understanding of machine learning, this book will get you started.