Comparative analysis of the artificial neural network training algorithms
Abstract
Comparative analysis of the artificial neural network training algorithms
Incoming article date: 04.12.2013There has been carried out the comparative analysis of the training algorithms of artificial neural networks of perceptron type: genetic, adaptive and hybrid.The comparison revealed that the adaptive algorithm is better coped with the task than the other algorithms. It is better to use the hybrid algorithm to solve the problem with complex target multiextremal function for which the adaptive algorithm is less convenient.
Keywords: artificial neural networks, multilayer perceptron, genetic, adaptive, hybrid algorithm