Crosscorrelation estimation using teacher forcing Hebbian learning and its application

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.