Introduction to Deep Learning

Catalog description

Introduces deep learning, covering fundamentals of neural networks, including architecture, computation graphs, computation theories, backpropagation, and gradient descent. Deep learning architectures including multilayer perceptrons (MLP), convolutional neural networks (CNN), recurrent neural networks (RNNs). Advanced architectures and methods such as transformers, generative DL, and graph neural networks. Coursework includes building and training deep learning architectures using popular packages such as NumPy and PyTorch. Most projects will prohibit AI, but at least one project will require AI. Prior background in machine learning is not assumed. Prerequisites: Familiarity with Python programming; and CS 375 and MATH 304 and either MATH 327 or MATH 448; or equivalents. Typically offered once every academic year.