Presenter
Chris Eliasmith, University of Waterloo
Dr. Chris Eliasmith is jointly appointed in Philosophy and Systems Design Engineering, and cross-appointed to Computer Science at the University of Waterloo. He has supervised students in each of these departments as well as Biology and Psychology. Centre for Theoretical Neuroscience (CTN) He is currently the director of this Centre. The Centre is a focal point for researchers across faculties (math, engineering, arts, science) interested in computational and theoretical models of neural systems. The Computational Neuroscience Research Group (CNRG) is his research lab, and is part of the CTN. He is the head of the lab.
Summary:
The large-scale model of the brain, Spaun, has undergone significant development. In
this talk, I describe how it has more than doubled in size, to 6.3 million neurons, 20 billion
connections, and significantly increased in functionality. New functions include the ability to
adapt online to changes in motor dynamics, classification of over 1000 categories of images, and
perhaps most importantly the ability to perform simple “mental gymnastics”. In this talk I
describe the semantic pointer architecture (SPA) that is used to construct the model,
demonstrate Spaunās abilities, and discuss future plans for improving on what is currently the
world’s largest functional brain model.
Challenges:
I would like there to be efficient large-scale computational platforms for models like Spaun, that run in real time.