Title :
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
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;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.548905
