Generative adversarial network

As explained in Build a Text-to-Image Generator (from Scratch)

A generative adversarial network is a generative model trained through competition between a generator that creates samples and a discriminator that distinguishes generated samples from real data.

A generative adversarial network (GAN) is a generative model built around competition between two neural networks: a generator creates synthetic samples from random noise, while a discriminator classifies samples as real or fake. section 11.4.1

Training alternates between two opposing objectives:

• The discriminator improves its ability to distinguish training data from generated data. section 11.4.1
• The generator improves its samples by making them harder for the discriminator to identify as fake. section 11.4.1
• At the idealized endpoint, generated samples become difficult to distinguish from real samples, and discriminator accuracy approaches 50 percent. section 11.4.1

GANs can produce highly realistic and diverse outputs, including images and music, but training may be unstable, collapse to limited modes, or provide poorly structured representations. VQGAN addresses these limitations by combining adversarial training with the discrete latent structure of a VQ-VAE. section 11.4 section 11.6

Figure 11.1 Eight steps for building a text-to-image generator from scratch. This chapter focuses on step 7: transforming an image into a sequence of integers using VQGAN. By achieving this, we unlock the ability to generate images sequentially with transformer models, a critical advance that powers state-of-the-art systems such as DALL-E.

Situates VQGAN within a text-to-image pipeline where adversarial generation supports converting images into discrete sequences for transformer-based generation. section 11.0

How Build a Text-to-Image Generator (from Scratch) covers it

How deep it goes

Defines the two-network minimax process and its ideal outcome, while deferring implementation and detailed loss equations.

Examples

Uses random noise, real and synthetic samples, image synthesis, music generation, and VQGAN image-token conversion as examples.

What you can do after

Evaluate GAN generation through generator-discriminator behavior, adversarial training dynamics, and known failure modes.

How it connects

Connects generators and discriminators with VQ-VAE, VQGAN, latent representations, quantization, and transformer-based text-to-image models.

liveBookmanning.com

Read Build a Text-to-Image Generator (from Scratch) on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA generative deep-learning model consisting of a generator and discriminator trained adversarially to produce realistic samples.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA generative adversarial network, a model family trained with a generator and discriminator to synthesize realistic data or transform data between domains.
• 

  liveBookmanning.com
  Outlier Detection in PythonA generative adversarial network is a model consisting of a generator and discriminator trained competitively so the generator produces data resembling a reference distribution.
• 

  liveBookmanning.com
  Grokking Machine LearningA generative adversarial network is a generative model composed of competing generator and discriminator networks that learn to produce realistic data.
• 

  liveBookmanning.com
  Sutskever's ListA generative adversarial network is a model architecture in which a generator creates candidates and a discriminator learns to distinguish them from genuine data.
• 

  liveBookmanning.com
  Generative AI in ActionA generative adversarial network is a generative model composed of a generator and discriminator trained adversarially to produce realistic synthetic data.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksA generative adversarial network is a model consisting of a generator and discriminator trained in opposition to produce realistic synthetic data.
• 

  liveBookmanning.com
  Data Without LabelsA generative adversarial network is a generative model consisting of a generator and discriminator trained adversarially to produce realistic samples.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA generative adversarial network is a deep learning architecture consisting of a generator and discriminator trained adversarially to produce samples resembling real data.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionA generative adversarial network is a model composed of a generator and discriminator trained through competition between synthetic-data creation and authenticity evaluation.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA generative adversarial network is a machine-learning model consisting of a generator and a discriminator trained through competition to produce increasingly realistic synthetic data.

Compare how 12 books explain generative adversarial network →

Related concepts

• generatorhas part · A generator is a computational component or construct that produces data or values from inputs, representations, context, or specified constraints.
• discriminatorhas part · A discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.
• VQGANincludes · VQGAN is a generative model that combines vector-quantized discrete latent representations with adversarial and perceptual objectives to synthesize images.
• generative modelingkind of · Generative modeling is a machine-learning approach that learns patterns or a data distribution to generate new samples resembling the data.
• DCGAN / deep convolutional ganincludes · A deep convolutional generative adversarial network is a GAN whose generator and discriminator use deep convolutional neural-network architectures.
• generationkind of · Generation is the computational production of new outputs, such as text or other content, from learned patterns and supplied inputs or context.

This explainer was generated by Manning's knowledge graph from the text of Build a Text-to-Image Generator (from Scratch). The section links point to the parts of the book it draws on.