NB/CNS Seminar- Speaker: Bruno Olshausen | Tuesday, April 9, 2024 at 4 pm

Date: Tuesday, April 9, 2024

Time: 4 pm

Location: Chen 100

Speaker – Bruno A. Olshausen

Professor

Helen Wills Neuroscience Institute, and Herbert Wertheim School of Optometry & Vision Science Director, Redwood Center for Theoretical Neuroscience

UC Berkeley

Faculty Host: Markus Meister

The goal of building machines that can perceive and act in the world as humans and other animals do has been a focus of AI research efforts for over half a century. Over this same period, neuroscience has sought to achieve a mechanistic understanding of the brain processes underlying perception and action. It stands to reason that these parallel efforts could inform one another. However recent advances in deep learning and transformers have, for the most part, not translated into new neuroscientific insights; and other than deriving loose inspiration from neuroscience, AI has mostly pursued its own course which now deviates strongly from the brain. Here I propose an approach to building both invariant and equivariant representations in vision that is rooted in observations of animal behavior and informed by both neurobiological mechanisms (recurrence, dendritic nonlinearities) and mathematical principles (group theory). What emerges from this approach is a neural circuit for factorization that can learn about shapes and their transformations from image data, and a model of the grid-cell system based on high-dimensional encodings of residue numbers. These models provide efficient solutions to long-studied problems that are well-suited for implementation in neuromorphic hardware or as a basis for forming hypotheses about visual cortex and entorhinal cortex.