This repo contains code for the labs of the 2020 Deep Learning course of the MSc in Artificial Intelligence at the University of Amsterdam.
In this assignment you will learn how to implement and train basic neural architectures like MLPs and CNNs for classification tasks.
The assignment consists of three parts. First, you will get familiar with vanilla RNNs and LSTMs on a simple toy problem. This will help you understand the fundamentals of recurrent networks. After that, you will study a more advanced LSTM cell to emphasize the wide variety in LSTM cells. In the final part, you will use LSTMs for learning and generating text. In addition to the coding assignments, the text contains multiple questions which you need to answer.
In this assignment, we focus on two—currently most popular—deep generative models, namely Variational Auto Encoders (VAE) and Generative Adversarial Networks (GAN). You will implement both in PyTorch as part of this assignment.