Study on RBF neural network based on swarm intelligence

Particle swarm optimization (PSO) is one of swarm intelligence. It was modified by escape of the particle velocity, and a self-adaptive PSO (SAPSO) was proposed to overcome the PSO shortcomings of the premature convergence and the local optimization. The SAPSO is combined with radial basis function (RBF) neural network to form a SAPSON hybrid algorithm. Compared with radial basis function neural network, SAPSON has less adjustable parameters, faster convergence speed, global optimization and higher identification precision in the numerical experiment.

[1]  J. D. Powell,et al.  Radial basis function approximations to polynomials , 1989 .

[2]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[3]  Randall S. Sexton,et al.  Reliable classification using neural networks: a genetic algorithm and backpropagation comparison , 2000, Decis. Support Syst..

[4]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[5]  Yue Shi,et al.  A modified particle swarm optimizer , 1998, 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360).

[6]  Piao Xiang-fan.  Study on Hidden Layer Evaluation for Feed-Forward Neural Networks , 2004 .

[7]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[8]  Mauro Birattari,et al.  Swarm Intelligence , 2012, Lecture Notes in Computer Science.