Evolutionary Algorithm for Optimal Connection weights

A neural network may be considered as an adaptive system that progressively self-organizes in order to approximate the solution, making the problem solver free from the need to accurately and unambiguously specify the steps towards the solution. Moreover, Evolutionary computation can be integrated with artificial Neural Network to increase the performance at various levels; in result such neural network is called Evolutionary ANN. In this paper very important issue of neural network namely adjustment of connection weights for learning presented by Genetic algorithm over feed forward architecture. To see the performance of developed solution comparison has given with respect to well established method of learning called gradient decent method. A benchmark problem of classification, XOR, has taken to justify the experiment. Presented method is not only having very probability to achieve the global minima but also having very fast convergence