A Hybrid Learning Approach to Blind Deconvolution of Linear

In this letter we presentahybrid network which performs blind deconvolution of linear MIMO systems. The hybrid network consists of a feedforward network followed by a feedback network, where each of synapses is represented by an FIR filter. The FIR synapses in the feedforward network are learned by a Godard cost based algorithm and the FIR synapses in the feedbacknetwork are updated by a spatio-temporal decorrelation algorithm so that different sources are recovered at different output nodes. We present an efficient spatiotemporal decorrelation algorithm based on the natural gradient. The validity of the proposed method is confirmed by computer simulations