ASSET Seminar: Neurosymbolic Programming for Science (Swarat Chaudhuri, University of Texas at Austin)

PRESENTATION ABSTRACT 

Neurosymbolic programming (NSP) is an emerging area of computing that bridges the fields of deep learning and program synthesis. Like in classical machine learning, the goal here is to learn functions from data. However, these functions are represented as programs that use neural network modules as well as symbolic primitives and are induced using a mix of symbolic search and gradient-based optimization. 

In this talk, I will give an elementary introduction to NSP and show how methods in this area have natural applications in accelerating scientific discovery. Specifically, using applications in behavioral neuroscience, I will show that NSP offers natural ways of incorporating prior knowledge into data-driven scientific discovery and interpreting discovered knowledge. I will conclude with a discussion of some of the open technical challenges in NSP in general and NSP-for-science in particular. 

BIO

Swarat Chaudhuri is a Professor of Computer Science and the director of the Trishul laboratory at UT Austin. His research lies at the interface of programming languages, formal methods, and machine learning. Through a synthesis of ideas from these areas, he seeks to develop a new generation of intelligent systems that are reliable, transparent, and secure by construction and can solve reasoning-intensive tasks beyond the scope of contemporary AI. He has received the NSF CAREER award, the ACM SIGPLAN John Reynolds Dissertation award, Meta and Google Research awards, and several ACM SIGPLAN and SIGSOFT distinguished paper awards. He is an associate editor for ACM Transactions on Programming Languages and Systems and an action editor for Transactions on Machine Learning Research. He served as a Program Chair for CAV 2016 and will be a Program Chair for ICLR 2024.