Let's talk about GAN and Fine-Tuning

Two topics I'm excited to talk about

Starting with GAN

go look at this website

a really fascinating example of GAN

this site generates superrealistic human faces in seconds

and no

it does not have a database and with each refresh it generates a complete new face

using GAN

Generative Adversarial Networks

what is it then?

well

GANs are a model architecture for training a generative model

first introduced in 2014

GAN uses two sub-models

Generator and Discriminator

Generator is responsible to generate from the given data and discriminator has to say if it is fake or not

the practice and learn continues till the discriminator is unable to tell if generated data is fake or real