What is a Generative Adversarial Network, GANs
Machine learning models
--
Generated Adversarial Networks aren’t manipulating images of real people — they’re creating nonexistent people. — Matthieu Bourel.
Unlike deep fakes, which alter real images of people, GANs generate images of people who don’t actually exist.
The purpose of GANs is not to impersonate specific individuals or commit identity theft, but rather to capture the basic features of human appearance and gradually improve their accuracy in doing so.
A Generative Adversarial Network (GAN) is a type of artificial intelligence (AI) system that is used for generating new data that is similar to the data it was trained on.
The GAN consists of two main components: a generator network and a discriminator network.
The generator network creates new data samples, while the discriminator network evaluates the authenticity of the generated samples by comparing them to the real data.
During the training process, the generator network learns to create samples that are increasingly more realistic, while the discriminator network becomes more effective at distinguishing real data from the generated samples.
This leads to a back-and-forth process of the two networks competing against each other until the generator produces samples almost indistinguishable from the real data.
GANs have many applications, including generating realistic images, creating new music and sound effects, and even generating new text.
They have shown great promise in various fields, including art, gaming, and medical research.
In other words…It is a class of machine learning models that consists of two main components: a generator and a discriminator.
GANs are designed to generate new data samples that are similar to a training dataset.
