DCGAN / deep convolutional gan

Q: How deeply does Evolutionary Deep Learning: Genetic algorithms and neural networks cover DCGAN / deep convolutional gan?

Explains architecture, hyperparameters, compilation, and alternating training, while deferring detailed convolution theory.

As explained in Evolutionary Deep Learning: Genetic algorithms and neural networks

A deep convolutional generative adversarial network is a generative adversarial network whose generator and discriminator use convolutional neural-network architectures.

A DCGAN is a generative adversarial network whose generator and discriminator use convolutional neural-network architectures. The generator maps random latent vectors to images, while the discriminator distinguishes real training images from generated ones. section 9.1.2

A practical DCGAN implementation typically proceeds as follows:

Prepare image data, optionally extracting one class to shorten training; a class value of 5 selects handwritten digit fives. section 9.1.2

Training and experimentation

Train on a single MNIST class to reduce runtime, inspect ten epochs of output, then rerun with all classes, Fashion-MNIST, or another supported dataset such as CIFAR. section 9.1.2 section 9.4.1

The model can also serve as a target for genetic-algorithm optimization. Discretizing gene values avoids reevaluating equivalent candidates, while fitness combines real, generated, and fake losses rather than relying on accuracy alone. section 9.5

How Evolutionary Deep Learning: Genetic algorithms and neural networks covers it

Cover of Evolutionary Deep Learning: Genetic algorithms and neural networks

liveBook manning.com

Read Evolutionary Deep Learning: Genetic algorithms and neural networks on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

Learn Generative AI with PyTorchA deep convolutional generative adversarial network architecture for image generation.

Compare how 2 books explain DCGAN / deep convolutional gan →

Related concepts

generative adversarial networkkind of · A generative adversarial network is a generative model with a generator and discriminator trained in competition, enabling the generator to produce samples resembling a target dataset or distribution.
genetic algorithmaddressed by · A genetic algorithm is an evolutionary optimization method that improves a population of candidate solutions through fitness-based selection and variation, often including recombination and mutation.
generatoruses · A generator is a computational component or construct that produces data or values from inputs, representations, context, or specified constraints.
discriminatoruses · A discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.

This explainer was generated by Manning's knowledge graph from the text of Evolutionary Deep Learning: Genetic algorithms and neural networks. The section links point to the parts of the book it draws on.