To improve the training time of BP neural networks

It is one of the most important tasks to improve the training time in the back-propagation (BP) neural networks. In the paper two methods based on error back propagation by adopting dynamic adjusting weights for reduction of the training time are presented. These approaches are based on an adequate modification of the traditional and classical methods. Some interesting results of computer experiments with the modified BP algorithm are provided. These results prove that these new methods are effective to solve some problems and faster than the traditional methods for training multi-layer feed-forward neural networks