| |
Apr 20, 2026
|
|
|
|
|
AI 4033 Reinforcement Learning
(3 hours)
This course provides a comprehensive introduction to deep learning, focusing on the design, implementation, and application of modern neural network architectures. Key topics include training, validation, and testing of deep learning models, optimization techniques, regularization strategies, and handling overfitting. Students will explore various deep neural network architectures, including feed-forward networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and graph neural networks (GNNs). Learning methods such as stochastic gradient descent, backpropagation, and advanced generative approaches (e.g., variational autoencoders and generative adversarial networks) are covered. Prerequisite: CS 4103 Fundamentals of Machine Learning or ECE 4413 Neural Networks and Deep Learning.
Add to Bulletin (opens a new window)
|
|
