Differential evolution for neural networks learning enhancement.

Abstract

In this paper ,we use new treatment ,Differential Evolution,, Differential Evolution (DE) has been used todetermine optimal value for ANN parameters such as learning rate and momentum rate and also for weightoptimization. In ANN, there are many elements need to be considered, and these include the number of input nodes,hidden nodes, output nodes, learning rate, momentum rate, bias parameter, minimum error and activation/transferfunctions. Three programs have developed; Differential Evolution Neural Network (DENN), Genetic Algorithm NeuralNetwork (GANN) and Particle Swarm Optimization with Neural Network (PSONN) to probe the impact of thesemethods on ANN learning using various datasets. The results have revealed that DENN has given quite promisingresults in terms of convergence rate and smaller errors compared to PSONN and GANN.