PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Information bottleneck optimization and independent component extraction with spiking neurons
Stefan Klampfl, Robert Legenstein and Wolfgang Maass
In: NIPS 2006, 04 Dec - 07 Dec 2006, Vancouver, Canada.

Abstract

We show that information bottleneck optimization and extraction of independent components can be implemented with stochastic spiking neurons with refractoriness. The new learning rule that achieves this is derived from information optimization principles. Furthermore, we demonstrate that extraction of independent components can be implemented in a biologically realistic way using interneurons.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
ID Code:2589
Deposited By:Wolfgang Maass
Deposited On:22 November 2006