Introduction to Neural Networks

Undergraduate / Graduate

This course will provide an introduction to neural networks and fundamental concepts in deep learning. It will cover the basics of training neural networks, including backpropagation, stochastic gradient descent, regularization, and data augmentation. It will explore network design principles, spanning multilayer perceptrons, convolutional and recurrent architectures, attention, memory, and generative adversarial networks. Students will gain experience applying neural networks to modern problems in computer vision, natural language processing, and reinforcement learning. Note: students can use at most one of CMSC 25500 and TTIC 31230 towards the computer science major.