Learning rate for the back propagation algorithm based on modified scant equation

Abstract EN

The classical Back propagation method (CBP) is the simplest algorithm for training feed-forward neural networks.

It uses the steepest descent direction with fixed learning rate a to minimize the error function E, since a is fixed for each iteration this causes slow convergence for the CBP algorithm.

In this paper we suggested a new formula for computing learning rate ak, using modified secant equation to accelerate the convergence of the CBP algorithm.

Simulation results are presented and compared with other training algorithms