Authors: Pratik R. Hajare; Narendra G. Bawane; Poonam T. Agarkar
Addresses: G.H. Raisoni College of Engineering, Nagpur, Maharashtra, India ' S.B. Jain Institute of Technology, Management and Research, Nagpur, Maharashtra, India ' Rajiv Gandhi College of Engineering and Research, Nagpur, Maharashtra, India
Abstract: This paper introduces particle swarm intelligence (PSI) in feed forward neural network (FFNN) with backpropagation for finding initial weights and biases of the feed forward neural network. The combination of particle swarm optimisation (PSO) and FFNN greatly help in fast convergence of FFNN in classification and prediction to various benchmark problems by overcoming the disadvantage of backpropagation of getting stuck at local minima or local maxima. The benchmarking databases for neural network contain various datasets from various different domains. All datasets represent realistic problems which could be called diagnosis tasks and all but one consist of real world data. Two such benchmarking problems are selected in this paper for comparison and the performance of PSO with FFNN for finding weights and biases is implemented and compared with random initialisation of weights and biases with normal FFNN. The result shows that using PSO minimises the prediction error.
Keywords: particle swarm optimisation; PSO; feedforward neural networks; FFNN; backpropagation; convergence; benchmarking; realistic problems; prediction error; local minima; local maxima; optimum weights; biases.
International Journal of Granular Computing, Rough Sets and Intelligent Systems, 2015 Vol.4 No.1, pp.39 - 46
Available online: 16 Feb 2016 *Full-text access for editors Access for subscribers Purchase this article Comment on this article