GAN (Generative Adversarial Network) machine learning models used to generate realistic data that resembles the data it was train on. These models consist in two components, a generator and a discriminator, both being neural networks. During the training process the generator takes a random input and tries to produce data that is realistic enough to fool the discriminator, while the discriminator tries to identify the fake dat genrated by the generator. In this way both networks ae trained in a feedback loop, where the generator tries to produce more realistic data to fool the discriminator and the discriminator becomes better at clasifying real data from fake data. This process is what give GANs its name, its name, they are adversarial because the two networks are competing against each other. As the two networks continue to improve, the generated data becomes more and more similar to the training data, resulting in highly realistic and diverse output. GANs have been used in a variety of applications, including image and video generation, music synthesis, and natural language processing.
| General | |
|---|---|
| Relese date | 2014 |
| Type | Machine Learning Framework |
Discover GAN
- GAN Paper Original Generative Adversarial Network Paper
.png&w=96&q=75){kind=small}
.png&w=96&q=75){kind=small}
.png&w=96&q=75){kind=small}
