Feed Forward Neural Network Optimization by Particle Swarm Intelligence

This paper is based on feed forward neural network (FFNN) optimization by particle swarm intelligence (PSI) used at the starting point of neural network for initial guess to weights and biases. Once the weights and biases are found, the same are used to train the neural network for prediction and classification benchmark problems. Further the trained neural network is the used to predict future sample and classify the test samples. A comparison is made between normal FFNN with random weights and biases and FFNN with particle swarm optimized weights and biases. Four such benchmark databases are considered in this paper, The Mackey Series, Box Jenkins Database, Breast Cancer Database and the Diabetic Database. Result shows that neural network performs better with initial weights and biases obtained by Particle Swarm optimization. The tendency of back propagation to stuck at local minima and local maxima thus can be overcome, and the network converges faster. Also the prediction error is minimized and classification accuracy is increased.