A Novel Cascaded Nonlinear Equalizer Configuration on Recurrent Neural Network Framework for Communication Channel

configuration has been proposed where a discrete cosine transform (DCT) block is embedded within the framework of a conventional RNN structure. The RNN module needs training and involves updation of the connection weights using the standard RTRL algorithm, which necessitates the determination of errors at the nodes of the RNN module. To circumvent this difficulty, an adhoc solution has been suggested to back propagate the output error through this heterogeneous configuration. Performance analysis of the proposed Recurrent Transform Cascaded (RTCS) equalizer for standard communication channel models show encouraging results.