This repository is made as supplementary material for a tutorial. The tutorial shows how to use Recurrent Neural Nets as generative models.

GAN to generate digits in MNIST dataset

A machine learning project that repurposes Bernoulli Naive Bayes as a generative model to synthesize handwritten digits from the MNIST dataset. Implements pixel-wise probability learning, sampling, and image generation with smoothing techniques.

This is a digit generation project that employs Generative Adversarial Networks (GANs) to generate realistic handwritten digits.

Generated digits (Similar to the ones in the MNIST dataset) using Wasserstein GANs.