CSCI 7745 Graduate Machine Learning

This course provides a broad graduate-level overview of the field of machine learning, including theoretical foundations and contemporary architectures and algorithms. Topics include supervised, self-supervised, and reinforcement learning; optimization techniques; model capacity and generalization, regularization; neural networks; representation learning, generative models; transfer learning, few-shot learning; contrastive learning; large language models; graph neural networks. Additional topics as time allows. Prerequisites: CSCI 7744 Foundations of Probability & Statistical Learning or equivalent.