Meta-learning functional plasticity rules in neural networks

Schedule
Wednesday, January 18, 2023
05:00 UTC
Tim Vogels

Institute of Science and Technology (IST), Klosterneuburg, Austria

Host: van Vreeswijk TNS

Event Information

Host

van Vreeswijk TNS

Duration

70 minutes

Abstract

Synaptic plasticity is known to be a key player in the brain’s life-long learning abilities. However, due to experimental limitations, the nature of the local changes at individual synapses and their link with emerging network-level computations remain unclear. I will present a numerical, meta-learning approach to deduce plasticity rules from either neuronal activity data and/or prior knowledge about the network's computation. I will first show how to recover known rules, given a human-designed loss function in rate networks, or directly from data, using an adversarial approach. Then I will present how to scale-up this approach to recurrent spiking networks using simulation-based inference.

We use essential cookies to run the site. Analytics cookies are optional and help us improve World Wide. Learn more.