Neural Network Learning Based on Chaotic Imperialist Competitive Algorithm

Abstract

Imperialist Competitive Algorithm (ICA) is a novel optimization algorithm that inspired by socio-political process of imperialistic competition. ICA shown its excellent capability in diverse optimization tasks. In this paper, a new method for training an Artificial Neural Network using Chaotic Imperialist Competitive Algorithm is proposed. In Chaotic Imperialist Competitive Algorithm (CICA) the chaos theory has been used to adjust the movement angle of colonies towards the imperialists. Using Chaotic Imperialist Competitive Algorithm (CICA), the weights of the Neural Network in its training phase are updated. In this paper, a multi layer Perceptron Neural Network used for prediction of the maximum worth of the stocks change in Tehran's Bourse Market. We trained this Neural Network with CICA, ICA, PSO and GA algorithms and compared the experimental results obtained from these four methods. The consideration of results showed that the training and test error of the network trained by CICA algorithm has been reduced in comparison to the other three methods. However, the run time of the proposed algorithm in training the neural network is less than PSO and GA algorithm it is a little more than ICA algorithm.