book

Generative Deep Learning

by David Foster

June 2019

Intermediate to advanced

327 pages

7h 36m

English

O'Reilly Media, Inc.

Read now

Unlock full access

Objective and ApproachPrerequisitesOther ResourcesConventions Used in This BookUsing Code ExamplesO’Reilly Online LearningHow to Contact UsAcknowledgments
What Is Generative Modeling?Generative Versus Discriminative ModelingAdvances in Machine LearningThe Rise of Generative ModelingThe Generative Modeling FrameworkProbabilistic Generative ModelsHello Wrodl!Your First Probabilistic Generative ModelNaive BayesHello Wrodl! ContinuedThe Challenges of Generative ModelingRepresentation LearningSetting Up Your EnvironmentSummary
Structured and Unstructured DataDeep Neural NetworksKeras and TensorFlowYour First Deep Neural NetworkLoading the DataBuilding the ModelCompiling the ModelTraining the ModelEvaluating the ModelImproving the ModelConvolutional LayersBatch NormalizationDropout LayersPutting It All TogetherSummary
The Art ExhibitionAutoencodersYour First AutoencoderThe EncoderThe DecoderJoining the Encoder to the DecoderAnalysis of the AutoencoderThe Variational Art ExhibitionBuilding a Variational AutoencoderThe EncoderThe Loss FunctionAnalysis of the Variational AutoencoderUsing VAEs to Generate FacesTraining the VAEAnalysis of the VAEGenerating New FacesLatent Space ArithmeticMorphing Between FacesSummary
GanimalsIntroduction to GANsYour First GANThe DiscriminatorThe GeneratorTraining the GANGAN ChallengesOscillating LossMode CollapseUninformative LossHyperparametersTackling the GAN ChallengesWasserstein GANWasserstein LossThe Lipschitz ConstraintWeight ClippingTraining the WGANAnalysis of the WGANWGAN-GPThe Gradient Penalty LossAnalysis of WGAN-GPSummary
Apples and OrgangesCycleGANYour First CycleGANOverviewThe Generators (U-Net)The DiscriminatorsCompiling the CycleGANTraining the CycleGANAnalysis of the CycleGANCreating a CycleGAN to Paint Like MonetThe Generators (ResNet)Analysis of the CycleGANNeural Style TransferContent LossStyle LossTotal Variance LossRunning the Neural Style TransferAnalysis of the Neural Style Transfer ModelSummary
The Literary Society for Troublesome MiscreantsLong Short-Term Memory NetworksYour First LSTM NetworkTokenizationBuilding the DatasetThe LSTM ArchitectureThe Embedding LayerThe LSTM LayerThe LSTM CellGenerating New TextRNN ExtensionsStacked Recurrent NetworksGated Recurrent UnitsBidirectional CellsEncoder–Decoder ModelsA Question and Answer GeneratorA Question-Answer DatasetModel ArchitectureInferenceModel ResultsSummary
PreliminariesMusical NotationYour First Music-Generating RNNAttentionBuilding an Attention Mechanism in KerasAnalysis of the RNN with AttentionAttention in Encoder–Decoder NetworksGenerating Polyphonic MusicThe Musical OrganYour First MuseGANThe MuseGAN GeneratorChords, Style, Melody, and GrooveThe Bar GeneratorPutting It All TogetherThe CriticAnalysis of the MuseGANSummary

Reinforcement LearningOpenAI GymWorld Model ArchitectureThe Variational AutoencoderThe MDN-RNNThe ControllerSetupTraining Process OverviewCollecting Random Rollout DataTraining the VAEThe VAE ArchitectureExploring the VAECollecting Data to Train the RNNTraining the MDN-RNNThe MDN-RNN ArchitectureSampling the Next z and Reward from the MDN-RNNThe MDN-RNN Loss FunctionTraining the ControllerThe Controller ArchitectureCMA-ESParallelizing CMA-ESOutput from the Controller TrainingIn-Dream TrainingIn-Dream Training the ControllerChallenges of In-Dream TrainingSummary
Five Years of ProgressThe TransformerPositional EncodingMultihead AttentionThe DecoderAnalysis of the TransformerBERTGPT-2MuseNetAdvances in Image GenerationProGANSelf-Attention GAN (SAGAN)BigGANStyleGANApplications of Generative ModelingAI ArtAI Music

Content preview from Generative Deep Learning

Chapter 9. The Future of Generative Modeling

I started writing this book in May 2018, shortly after the “World Models” paper discussed in Chapter 8 was published. I knew at the time that I wanted this paper to be the focus of the final core chapter of the book, as it is the first practical example of how generative models can facilitate a deeper form of learning that takes place inside the agent’s own world model of the environment. To this day, I still find this example completely astonishing. It is a glimpse into a future where agents learn not only through maximizing a single reward in an environment of our choice, but by generating their own internal representation of an environment and therefore having the capability to create their own reward functions to optimize. In this chapter, we will run with this idea and see where it takes us.

First, we must place ourselves at the very edge of the generative modeling landscape, among the most radical, innovative, and leading ideas in the field. Since the inception of this book, significant advancements in GAN and attention-based methodologies have taken us to the point where we can now generate images, text, and music that is practically indistinguishable from human-generated content. We shall start by framing these advancements alongside examples that we have already explored and walking through the most cutting-edge architectures available today.