In this project, I use Generative Adversarial Networks (GAN) to generate MNIST image data.

In a GAN, one neural network, called the generator, generates new data instances, while the other, the discriminator, evaluates them for authenticity; i.e. the discriminator decides whether each instance of data it reviews belongs to the actual training dataset or not.

MNIST data:

Training images: 60,000 Test images: 10,000