Separable Recursive Training Algorithms with Switching Module

A novel hybrid or separable recursive training strategies are derived for the training of feedforward neural networks which incoporates a switching module. This new technique for updating weights combines nonlinear recursive training algorithms for the optimization of nonlinear weights with recursive least square type algorithms for the training of linear weights in one integrated routine. The proposed new variant of hybrid weight update includes switching mechanism based on the condition of input data to the system (correlated or noncorrelated). Simulation results demonstrate the improvement of the new proposed switching mode training scheme.