Machine learning basics, generalization theory, training, validation, and testing. Introduction to artificial neural networks: feedforward, convolutional, recurrent networks. Types of layers in deep models. Architectural and memory calculations. Regularization and optimization. Hardware architectures for deep learning. The course culminates in a major project focusing on engineering applications of deep learning. Prerequisite: MATH 251, ENSC 280, ENSC 351, ENSC 380, all with a minimum grade of B. Students with credit for ENSC 813 may not take this course for further credit.
Machine learning basics, generalization theory, training, validation, and testing. Introduction to artificial neural networks: feedforward, convolutional, recurrent networks. Types of layers in deep models. Architectural and memory calculations. Regularization and optimization. Hardware architectures for deep learning. The course culminates in a major project focusing on engineering applications of deep learning. Prerequisite: MATH 251, ENSC 280, ENSC 351, ENSC 380, all with a minimum grade of B. Students with credit for ENSC 813 may not take this course for further credit.
