Guided convergence for training feed-forward neural network using novel gravitational search optimization

Abstract

Training of feed-forward neural network using stochastic optimization techniques recently gained a lot of importance invarious pattern recognition and data mining applications because of its capability of escaping local minima trap. However such techniques may suffer from slow and poor convergence. This fact inspires us to work on meta-heuristic optimization technique for training the neural network. In this respect, to train the neural network, we focus on implementing the gravitational search algorithm(GSA) which is based on the Newton's law of motion principle and the interaction of masses. GSA has good ability to search for the global optimum, but it may suffer from slow searching speed in the last iterations. Our work is directed towards the smart convergence by modifying the original GSA and also guiding the algorithm to make it immune to local minima trap. Results on various benchmark datasets prove the robustness of the modified algorithm.