Timezone: »

An online Hebbian learning rule that performs Independent Component Analysis
Claudia Clopath · André Longtin · Wulfram Gerstner

Wed Dec 05 10:30 AM -- 10:40 AM (PST) @

Independent component analysis (ICA) is a powerful method to decouple signals. Most of the algorithms performing ICA do not consider the temporal correlations of the signal, but only higher moments of its amplitude distribution. Moreover, they require some preprocessing of the data (whitening) so as to remove second order correlations. In this paper, we are interested in understanding the neural mechanism responsible for solving ICA. We present an online learning rule that exploits delayed correlations in the input. This rule performs ICA by detecting joint variations in the firing rates of pre- and postsynaptic neurons, similar to a local rate-based Hebbian learning rule.

Author Information

Claudia Clopath (EPFL)
André Longtin (Physics Department, University of Ottawa)
Wulfram Gerstner (EPFL)

More from the Same Authors