LATENT SPACE REPRESENTATION: A HANDS-ON TUTORIAL ON AUTOENCODERS IN TENSORFLOW

This is a part-1 of the series of tutorials that I am writing on unsupervised/self-supervised learning using deep neural networks. In this tutorial, the focus would be on latent space implementation using autoencoder architecture and its visualization using t-SNE embedding. Before we delve into code, lets define some important concepts which we will encounter throughout the tutorial. The real-world data is often redundant with high dimensions. This poses challenges not only for computational efficiency but also hinders the modelling of the representation.