Functional mapping of desired signals for improved performance of fully dynamic supervised neural networks with a fixed pole IIR structure

A new method is presented of functional mapping of the desired signal used for the training of dynamic supervised neural networks that contain fixed pole IIR structures. The idea is to pass the desired signal through the same number and form of nonlinearities as the data encounters as it passes from the input to the output layer. The neural network has three layers: a filterbank of fixed pole three IIR bandpass filters with variable gains, an intermediate layer of two multiplicative coefficients, and an output layer. The outputs of the input and intermediate layers are passed through logistic nonlinearities