Natural gradient learning for spatio-temporal decorrelation: Recurrent network

Seungjin Choi, Shunichi Amari, Andrzej Cichocki

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

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.

Original languageEnglish
Pages (from-to)2715-2722
Number of pages8
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE83-A
Issue number12
Publication statusPublished - Dec 2000
Externally publishedYes

Fingerprint

Dive into the research topics of 'Natural gradient learning for spatio-temporal decorrelation: Recurrent network'. Together they form a unique fingerprint.

Cite this