Communicating gradients for learning using activity dynamics

Speaker: Blake Richards , Canadian Institute for Advanced Research (CIFAR)

Date: Friday, April 26, 2019

Time: 4:00 PM to 5:00 PM

Public: Yes

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,

Relevant URL:

Speaker URL:

Speaker Photo:
Richards blakeheadshot bw sept2017

Reminders to:

Reminder Subject: 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.

Research Areas:
Algorithms & Theory, AI & Machine Learning

Impact Areas:

See other events that are part of the Brains, Minds and Machines 2018/2019.

Created by Kathleen Sullivan Email at Monday, February 04, 2019 at 11:48 AM.