Speaker: Mohit Kulkarni,Department of Mathematics, IIT Kanpur.
Title: Does the Brain do Backpropagation? A look into learning rules and synaptic plasticity.
During learning, the brain modifies synapses to improve behaviour. In the cortex, synapses are embedded within multilayered networks, making it difficult to determine the effect of an individual synaptic modification on the behaviour of the system. Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, Here we build on past and recent developments to argue whether an algorithm similar to backpropagation enables learning in the brain and modulates synaptic plasticity.