Deep Learning Systems in Engineering ENSC 813 (3)

Covers machine learning basics, generalization theory, training, validation and testing. Introduces artificial neural networks, feedforward networks, convolutional networks, and types of layers in deep models. Provides overview of hardware architectures for deep learning: architectural and memory calculations; regularization and optimization of deep learning models. Analyzes recurrent and discursive networks. Culminates in a major project focusing on engineering applications of deep learning in signal processing, communications, biomedical engineering, robotics, or other areas. Prerequisite: MATH 251 or ENSC 280 or ENSC 380 or permission of instructor. Students with credit for CMPT 880 - Special Topics in Computing Science: Deep Learning may not take this course for further credit.