Natural Gradient Learning for Spatio-Temporal Decorrelation: Recurrent Network

Seungjin CHOI
Shunichi AMARI
Andrzej CICHOCKI

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E83-A    No.12    pp.2715-2722
Publication Date: 2000/12/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
Keyword: 
adaptive decorrelation,  Hebbian learning,  natural gradient,  recurrent network,  spatio-temporal processing,  

Full Text: PDF>>
Buy this Article


Summary: 
Spatio-temporal decorrelation is the task of eliminating correlations between associated signals in spatial domain as well as in time domain. In this paper, we present a simple but efficient adaptive algorithm for spatio-temporal decorrelation. For the task of spatio-temporal decorrelation, we consider a dynamic recurrent network and calculate the associated natural gradient for the minimization of an appropriate optimization function. The natural gradient based spatio-temporal decorrelation algorithm is applied to the task of blind deconvolution of linear single input multiple output (SIMO) system and its performance is compared to the spatio-temporal anti-Hebbian learning rule.