Fall 2023 Colloquium - Gašper Beguš - AI Interpretability for Biological and Artificial Neural Processing of Language

Abstract: Interpretability is the new frontier in AI research. Understanding how generative models learn and how they resemble or differ from humans can bring insights for diverse fields such as neuroscience and decoding animal communication. In this talk, I present several techniques for introspecting deep neural networks. I also propose a model called ciwaGAN that features several aspects of human language acquisition that other models lack (embodiment, communicative intent, production-perception loop). Together, interpretability techniques and realistic models of human language can bring us closer to answering some of the fundamental questions about human and non-human language learning. Using the proposed techniques, we can compare and evaluate artificial and biological neural processing of language as well as discover meaningful patterns in data as unknown as that of whale communication.

Event Logistics: 3pm in Kerr 273 on October 23rd

Speaker Biography: Dr. Gašper Beguš is an Assistant Professor of Linguistics at UC Berkeley.