Minimization Algorithm for Training Feed Forward Neural Network

In this paper we suggested a new learning rate , which improves the classical Backpropagation algorithm (BP). The derivatation of are based on approximating the error function E to the quadratic one in sufficiently small neighborhood for the optimal weight vector. The suggested algorithm (Spectral Backpropagation SBP say) is tested and the experimental results show that the SBP learning strategy improves the considered methods. 1Introduction The batch training of a feed forward Neural network (FNN) is consistent with the theory of unconstrained optimization [5] and can be viewed as the minimization of the function E; that is to find a minimizer n n R w w w ) ,..., ( * * 1 * Such that: ) ( * w E Min w n R w (1) where E is the batch error measure defined as