Applied Math Colloquium | Jeff Orchard, Efficient Cognition with Spiking Neurons

MC 5501 

Speaker

Jeff Orchard, Cheriton School of Computer Science, University of Waterloo

Title

Efficient Cognition with Spiking Neurons

Abstract

Vector Symbolic Algebras (VSAs) offer a powerful framework for representing compositional reasoning. Their algorithms lend themselves to neural-network implementations, allowing us to create neural networks that can perform cognitive functions, like spatial reasoning, arithmetic, and symbolic logic. But the vectors involved can be quite large. Advances in neuromorphic hardware hold the promise of reducing the running time and energy footprint of spiking neural networks by orders of magnitude. In this talk, I will extend some pioneering work to run VSA algorithms on a substrate of spiking neurons, and demonstrate their power and versatility in several foundational problem domains, including spatial memory, function representation, and memory (i.e. signal delay).