Brains, Minds + Machines Seminar Series: Communicating gradients for learning using activity dynamics

Photo of Blake Richards
April 26, 2019 - 4:00 pm to 5:00 pm
Add to Calendar

Blake Richards, Assistant Professor, Associate Fellow of the Canadian Institute for Advanced Research (CIFAR)


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.



MIT Bldg 46-3002, 43 Vassar Street, Cambridge MA 02139
April 26, 2019
4:00 pm to 5:00 pm
Singleton Auditorium(46-3002)

MIT Bldg 46-3002, 43 Vassar Street, Cambridge MA 02139