— Deep Learning

Prerequisites & course information

Course Description: Deep learning theory, models, and applications. Mathematical foundations, optimization, multi-layer perceptrons, autoencoders, convolutional neural networks, recurrent neural networks (LSTM, GRU), generative adversarial networks, word embeddings, transformers, BERT, and graph neural networks. Hands-on experience implementing deep learning models using PyTorch for image classification, text classification and generation, and graph node classification. Learning Activities: Lecture 3 hour(s), Discussion 1 hour(s). Credit Limitation(s): No credit to students who have taken ECS 189G . Grade Mode: Letter. General Education: Science & Engineering (SE). This course version is effective from, and including: Fall Quarter 2026. Learning Activities: Lecture 3 hour(s), Discussion 1 hour(s). Credit Limitation(s): No credit to students who have taken ECS 189G . Grade Mode: Letter. General Education: Science & Engineering (SE).