Laboratory for Control, Learning, and Systems Biology

Papers by H. Dewan and E.D. Sontag

1990
  1. ▪H. Dewan, E.D. Sontag, "Extrapolatory methods for speeding up the BP algorithm", In Proc. Int. Joint Conf. on Neural Networks, Washington, DC, Jan. 1990, Lawrence Erlbaum Associates, Inc., Publishers, ISBN 0-8058-0775-6, pp. I.613–616, 1990. pdf
    machine learning · artificial intelligence · neural networks
    Abstract

    We describe a speedup technique that uses extrapolatory methods to predict the weights in a Neural Network using Back Propagation (BP) learning. The method is based on empirical observations of the way the weights change as a function of time. We use numerical function fitting techniques to determine the parameters of an extrapolation function and then use this function to project weights into the future. Significant computational savings result by using the extrapolated weights to jump over many iterations of the standard algorithm, achieving comparable performance with fewer iterations.