A Novel PSO Based Back Propagation Learning-MLP (PSO-BP-MLP) for Classification

Particle swarm optimization (PSO) is a powerful globally accepted evolutionary swarm intelligence method for solving both linear and non-linear problems. In this paper, a PSO based evolutionary multilayer perceptron is proposed which is intended for classification task in data mining. The network is trained by using the back propagation algorithm. An extensive experimental analysis has been performed by comparing the performance of the proposed method with MLP, GA-MLP. Comparison result shows that, PSO-MLP gives promising results in majority of test case problems.