Crosscorrelation estimation using teacher forcing Hebbian learning and its application

Author

Wang, Chum ; Wu, Hsiao-Chun ; Principe, J.C.

Author_Institution

Comput. NeuroEng. Lab., Florida Univ., Gainesville, FL, USA

Volume

1

fYear

1996

fDate

3-6 Jun 1996

Firstpage

282

Abstract

This paper proposes a new network architecture to compute the temporal crosscorrelation function between two signals, either stationary or local stationary. We show that the weights of a multi-FIR-like filter trained with a teacher forcing Hebbian rule encode the crosscorrelation function between the input and the desired response. This temporal correlation idea is applied to the blind sources separation problem. And experimental results are also given to show the validation of the idea

Keywords

FIR filters; Hebbian learning; correlation methods; filtering theory; neural net architecture; blind sources separation problem; crosscorrelation estimation; local stationary signals; multi-FIR-like filter; neural network architecture; teacher forcing Hebbian learning; temporal correlation; temporal crosscorrelation function; Application software; Backpropagation; Biological neural networks; Computer architecture; Decorrelation; Finite impulse response filter; Hebbian theory; Laboratories; Neural engineering; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.548905

Filename

548905