Course Details

Formerly offered as EECE 571F. From Fall 2026 onwards, the course is offered as EECE 576L: Advanced Topics in Deep Learning.

Detailed Overview

EECE 576L is a graduate course about the principles that shape modern deep learning systems. It connects three areas—geometric deep learning, probabilistic and generative modeling, and deep reinforcement learning—and emphasizes the assumptions and objectives that connect these model families.

The geometric deep learning portion begins with invariance and equivariance and develops neural architectures for sets, sequences, graphs, and data with group symmetries. We study set models, attention and Transformers, message-passing and graph-convolutional networks, and group-equivariant and steerable networks. Recent papers extend these ideas to visual geometry and atomistic foundation models. The goal is to understand the relationship between data structure and model inductive bias, including how symmetries guide parameter sharing and model design.

The probabilistic and generative modeling portion connects autoregressive language models with diffusion, score-based, and flow models. We compare their training objectives, parameterizations, and generation procedures, including masked diffusion language models, one-step generation, and inference-time alignment. This builds a common view of several major approaches to modern generative modeling.

The reinforcement learning portion introduces policy-gradient methods and learning from feedback for language-model post-training. Student presentations examine DPO, the effects of reinforcement learning with verifiable rewards, and DeepSeek-V3.2 as a case study of scalable post-training. Presentations on vision-language-action and world action models connect generative modeling to robotic control. These papers provide concrete examples of how data, model initialization, and optimization objectives shape learning dynamics.

The course combines instructor lectures, student-led presentations of recent research papers, and a substantial research project. Students practice identifying assumptions, evaluating evidence, explaining contributions and limitations, selecting appropriate baselines, and supporting conclusions with reproducible experiments or rigorous theory.

Learning Outcomes

By the end of the course, students should be able to:

Prerequisites

Grading

See the course project overview for group, scope, and deliverable expectations and the course policies for rules that apply to assessments.