An Efficient Backpropagation Learning Algorithm for Pattern Recognition

C.-C. Yu, Y.-C. Tang, and T.-M Lin, (Taiwan)

Keywords

Multilayer Feedforward neural networks, BP algorithm, Pattern recognition, Twospiral problem

Abstract

The standard back-propagation (BP) algorithm is basically a gradient-descent method, it has the problems of local minima and slow convergence. In this paper, a simple method based on the BP algorithm by employing an adaptive learning rate and momentum factor to reduce the training time is presented. Simulation results indicate a superior convergence speed as compared to other competing methods.

Important Links:



Go Back