Cengiz Pehlevan

Wednesday 26th June 2019

Time:4.00pm

Ground Floor Seminar Room

25 Howland Street, London, W1T 4JG

Gradient-based learning with Hebbian plasticity

Synaptic plasticity is widely accepted to be the mechanism behind learning in the brain’s neural networks (NNs). A central question is how synapses, which have access to only local information about the state of the network, can still organize collectively and perform circuit-wide learning in an efficient manner. We show that such local learning actually performs gradient-based optimization of a novel class of network-wide learning objectives. These objectives are based on similarities and contain a term that aligns the similarity of outputs to the similarity of inputs. Online optimization of these objectives leads to algorithms implementable by biologically-plausible NNs with local learning rules. Credit assignment problem is solved elegantly by a factorization of the network-wide learning objective to synapse specific local objectives. Similarity-based objectives and associated NNs solve unsupervised learning tasks relevant to the brain such as dimensionality reduction, sparse and/or nonnegative feature extraction, blind source separation, clustering and manifold learning. In addition to serving as models of natural NNs, such networks can serve as general-purpose machine learning algorithms.

Biography:
Cengiz (pronounced "Jen·ghiz”) Pehlevan is an Assistant Professor of Applied Mathematics at Harvard School of Engineering and Applied Sciences. His research interests are in theoretical neuroscience and neural computation. His group seeks to uncover the algorithms of the brain and their implementation at the network and cellular levels. Cengiz came to Harvard from the Flatiron Institute's Center for Computational Biology (CCB), where he was a a research scientist in the neuroscience group. Before CCB, Cengiz was a postdoctoral associate at Janelia Research Campus, and before that a Swartz Fellow at Harvard. Cengiz received a doctorate in physics from Brown University and undergraduate degrees in physics and electrical engineering from Bogazici University in Turkey.