EECE 571F

Deep Learning with Structures

Structures are pervasive in science and engineering. Some structures are conveniently observable, e.g., 3D point clouds, molecules, phylogenetic trees, social networks, whereas some are latent or hard to be measured, e.g., parse trees for languages/images, causal graphs, and latent interactions among actors in multi-agent systems. Advanced deep learning techniques have emerged recently to effectively process data in the above scenarios.

This course will teach cutting-edge deep learning models and methods with structures. In particular, for observable structures, we will introduce popular models, e.g., Transformers, Graph Neural Networks, with an emphasis on motivating applications, design principles, practical and or theoretical limitations, and future directions. For latent structures, we will introduce motivating applications, latent variable models (e.g., variational auto-encoders), and inference methods (e.g., amortization and search), and learning methods (e.g., REINFORCE and relaxation).

Prerequisite: Knowledge of basic machine learning, probabilities, statistics, and linear algebra is required. Proficiency with Python and familiarity with modern deep learning software packages including PyTorch or Tensorflow is required to finish the course project.

Instructor Renjie Liao

3 credits