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.
Topics
- 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
Topics explicitly listed in official catalogue description
Sources
- Course catalogue ↗2026-2027