Communicating gradients for learning using activity dynamics
, Canadian Institute for Advanced Research (CIFAR)
Date: Friday, April 26, 2019
Time: 4:00 PM to 5:00 PM
Location: Singleton Auditorium (46-3002)
Event Type: Seminar
Room Description: MIT Bldg 46-3002, 43 Vassar Street, Cambridge MA 02139
Host: Boris Katz & Tomaso Poggio
Contact: Kathleen Sullivan, firstname.lastname@example.org
Speaker URL: https://www.utsc.utoronto.ca/biosci/blake-richards
TALK: Communicating gradients for learning using activity dynamics
Abstract: Theoretical and empirical results in the neural networks literature demonstrate that effective learning at a real-world scale requires changes to synaptic weights that approximate the gradient of a global loss function. For neuroscientists, this means that the brain must have mechanisms for communicating loss gradients between regions, either explicitly or implicitly. Here, I describe our research into potential means of communicating loss gradients using the dynamics of activity in a population of neurons. Using a combination of computational modelling and two-photon imaging data, I will present evidence suggesting that the neocortex may encode loss gradients related to motor learning and sensory prediction using the temporal derivative of activity in populations of pyramidal neurons.
Algorithms & Theory, AI & Machine Learning
Created by Kathleen Sullivan at Monday, February 04, 2019 at 11:48 AM.