Hands-On Deep Learning for IoT

Generative adversarial networks

GANs are deep neural net architectures that consist of two networks pitted against each other (hence the name adversarial). Ian Goodfellow et al. introduced GANs in a paper (see more at https://arxiv.org/abs/1406.2661v1). In GANs, the two main components are the generator and discriminator:

Working principle of generative adversarial networks

In a GAN architecture, a generator and a discriminator are pitted against each other—hence the name, adversarial:

• The generator tries to generate data samples out of a specific probability distribution and is very similar to the actual object.
• The discriminator will judge ...