CSC 331 - Applied Deep Learning

Course Units:

This course introduces the theory and practice of deep learning (DL) through a hands-on approach. Students will explore the mathematical foundations of DL and will be exposed to the art of designing and training state-of-the-art DL architectures. Emphasis is placed on coding, experimentation, and delivering end-to-end solutions using open-source tools by applying the learned techniques to real-world problems in areas such as image classification and time-series analysis. Topics include neural networks, backpropagation,
optimization, convolutional neural networks (CNNs), advanced CNNs such as ResNets and DenseNets, modern recurrent nets including LSTM, attention mechanisms, transformers, and emerging models such as vision transformers (ViTs) and large language models (LLMs). Cross-Listed: ECE 331 Prerequisite(s): ECE 329 or CSC 321 or STA 264