GAN refers to Generative Adversarial Networks. Such networks is made of two networks that compete against each other. The first one generates new samples and the second one discriminates between generated samples and true samples.

GAN refers to Generative Adversarial Networks.

Such networks is made of two networks that compete against each other:

  • The first network generates new samples, based on random input samples to create variability

  • The second network discriminates between generated samples and true samples. It usually entails running the first network to generate a new sample and the discriminator network must tag it as artificial. At the same time, a true sample is passed in the discriminator to and this one must be tagged as non artificial.

By optimizing the first network in alternance with the second one, more and more realistic samples will be created by the generative network which can then be used without the discriminator once trained.

history | excerpt history