HIOPGA: A New Hybrid Metaheuristic Algorithm to Train Feedforward Neural Networks for Prediction

Most of neural network training algorithms make use of gradient-based search and because of their disadvantages, researchers always interested in using alternative methods. In this paper to train feedforward, neural network for prediction problems a new Hybrid Improved Opposition-based Particle swarm optimization and Genetic Algorithm (HIOPGA) is proposed. The opposition-based PSO is utilized to search better in solution space. In addition, to restrain model overfit with training pattern, a new cross validation method is proposed. Several benchmark problems with varying dimensions are chosen to investigate the capabilities of the proposed algorithm as a training algorithm. The result of HIOPGA is compared with standard backpropagation algorithm with momentum term.