AN IMPROVED BACK-PROPAGATION NEURAL NETWORKS USING A MODIFIED NON-LINEAR FUNCTION

摘要

Perhaps the backpropgation neural networks (BP) is the most widely used architecture in the filed of artificial neural networks, but still suffers from different difficulties. These would burden the complete success of this paradigm. However, in this paper we tried to overcome some of these problems, particularly, these that are concerned with the learning convergence rates, number of iterations, error ratios, and others. We have used a new proposed learning algorithm based on Bp. We have noticed that using a modified non-linear mapping function would enhance the whole process in terms of learning speed, convergence. Comparing our approach with the classical one, somebody, will notice that the enhancement is, really, noticeable. The new approach has been applied on different neural network architectures, and has shown tangible improvements.