Talk Title: Neuroscience, behavior, and what's in-between

Abstract: I'll present an overview of a forthcoming book about how we can link neuroscience to cognition and behavior. Drawing on several little-known results in early computer science, I'll describe how patterns in behavior can rigorously imply the existence of particular unobserved states and structures. This provides a foundation for linking behavioral regularities to what must be present in neural implementations. The resulting states are often re-describable in abstract terms more familiar to cognitive science, like "sets", "numbers", "stacks", etc. I'll highlight the implementation of "stacks", commonly used for grammars, and show how to characterize the space of possible neural implementations, including with subsystems/circuits operating in serial and parallel. The approach provides a set of concrete hypotheses, a guide for neural data analysis, and points towards a method for understanding structure in modern AI systems, including LLMs. I'll conclude by suggesting a Marr-like framework in which the bridges between levels can be made rigorous, connecting behavior, high-level theorizing, and neural implementation. 

Bio: I completed my PhD from MIT BCS in 2011. I was a postdoc and a faculty member at the University of Rochester until 2018, and then moved to psychology and neuroscience at UC Berkeley. My lab works on language, numerical cognition, and spanning cognition and computation. 

Webinar Link: https://us02web.zoom.us/j/89002014229?pwd=bzZuZGh6cVhOSjJ6TlNZVHgrRnNaQT09

Followed by a reception with food and drink in 3^rd floor atrium