PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

STDP performs stochastic EM to reveal the hidden causes of spatiotemporal spiking patterns
Bernhard Nessler, Michael Pfeiffer and Wolfgang Maass
In: NIPS 2009 Workshop: Bounded-rational analyses of human cognition: Bayesian models, approximate inference, and the brain, 12 Dec 2009, Whistler, Canada.

Abstract

Spike-timing dependent plasticity (STDP), in conjunction with a stochastic soft winner-take-all (WTA) circuit, induces spiking neurons to learn implicit internal models for subclasses (or “causes”) of the high-dimensional spike patterns of hundreds of pre-synaptic neurons. Our rigorous mathematical analysis shows that STDP is able to approximate a stochastic online Expectation-Maximization (EM) algorithm for modeling the input data.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:6089
Deposited By:Michael Pfeiffer
Deposited On:08 March 2010

[Edit]