Classification with Some Artificial Neural Network Classifiers Trained a Modified Particle Swarm Optimization
Erdinç Kolay, Taner Tunç, Erol Eğrioğlu · American Journal of Intelligent Systems · 2016
In this paper, we propose a new modified particle swarm algorithm for training some neural network classifiers for the most used classification problems in literature. Researches in artificial neural network field are based on different network architectures including multilayer perceptron, single multiplicative neuron and pi-sigma neuron model. To obtain a satisfactory performance for these classifiers, one of the most important issues is network training. Evolutionary algorithms are commonly used for training neural network classifiers. Particle swarm algorithm is population based, stochastic and meta-heuristic algorithm to solve optimization problems. As all evolutionary algorithms, the particle swarm algorithm may fall into local optimum and convergence rate may incredibly decline in iterative process. To overcome these shortcomings we refer to modify the particle swarm optimization with changing position matrix for each generation at iterative process. Experimental results show that training network with the proposed modified particle swarm optimization improve the classification performance for artificial neural network classifiers.