A DCGAN model (Deep Convolutional GAN)to generate some handwritten digits trained on the MNIST dataset(70,000).

GANs consist of two neural networks, A generator and a discriminator, playing a game of cat and mouse. The generator creates new data from by drawing from and manipulating a noise distribution, while the discriminator distinguishes between generated and real data drawn from a target distribution. Through this adversarial process, the generator learns to produce structurally realistic images, and the discriminator learns to distinguish real vs. fake, until the latter can no longer make confident distinctions.

1.) Numpy
2.) Matplotlib
3.) Tensorflow
4.) Keras

Adam Optimizer:
It is a stochastic gradient descent method that is based on adaptive estimation of first-order and second-order moments.

Loss Funtion:Binary CrossEntropy