Total least squares approach for fast learning in multilayer neural networks

Authors:
  • RPR. Parisi
    R. Parisi
  • ECE.D.D. Claudio
    E.D.D. Claudio
  • GOG. Orlandi
    G. Orlandi

Abstract
Classical methods for training feedforward neural networks are characterized by a number of shortcomings, first of all the slow rate of convergence and the occurrence of local minima. In this work a new learning algorithm is presented as a faster alternative to the Backpropagation method. The algorithm is based on the solution of a linearized system for each layer of the network performed by a block Total Least Squares technique. Simulation results are reported showing the high convergence speed of the new algorithm and its high degree of accuracy

This publication has 6 references indexed in Scilit: