Joint ICTP-SISSA seminar by Gabriel Ocker - Zoom meeting on 30 November 2021 at 16:00 CET

[Quantitative Life Sciences]

Dear All,

Tomorrow, Tuesday, 30 November  at 16:00 CET, Gabriel Ocker (Boston 
University) will give a seminar titled "Tensor decomposition of 
higher-order correlations by nonlinear Hebbian plasticity".


This seminar will be held jointly with Theoretical and Scientific Data 
Science (TSDS) at SISSA.

Abstract:
Biological synaptic plasticity exhibits nonlinearities that are not 
accounted for by classic Hebbian learning rules. Here, we introduce a 
simple family of generalized nonlinear Hebbian learning rules. We study 
the computations implemented by their dynamics in the simple setting of 
a neuron receiving feedforward inputs. These nonlinear Hebbian rules 
allow a neuron to learn tensor decompositions of its higher- order input 
correlations. The particular input correlation decomposed and the form 
of the decomposition depend on the location of nonlinearities in the 
plasticity rule. For simple, biologically motivated parameters, the 
neuron learns eigenvectors of higher-order input correlation tensors. We 
prove that tensor eigenvectors are attractors and determine their basins 
of attraction. We calculate the volume of those basins, showing that the 
dominant eigenvector has the largest basin of attraction. We then study 
arbitrary learning rules and find that any learning rule that admits a 
finite Taylor expansion into the neural input and output also has stable 
equilibria at generalized eigenvectors of higher-order input correlation 
tensors. Nonlinearities in synaptic plasticity thus allow a neuron to 
encode higher-order input correlations in a simple fashion.

Indico: http://indico.ictp.it/event/9747/

Zoom Meeting ID to attend the online seminar: 6902850337
Join Zoom Meeting: https://sissa-it.zoom.us/j/6902850337


-- 
Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-2240623
www.ictp.it/research/qls.aspx
e-mail:qls at ictp.it