A Hybrid Particle Swarm Optimization for Feed-Forward Neural Network Training

This paper employs a hybrid particle swarm optimization using optimal foraging theory (PSOOFT) for multilayer feed-forward neural network (MFNN) training. Three benchmark classification problems: Iris, Newthyroid and Glass are conducted to measure the performance of PSOOFT based MFNN. The simulation results are also compared with obtained using back Propagation (BP), genetic algorithm (GA) and standard PSO (SPSO) approaches to demonstrate the effectiveness and efficiency of PSOOFT.

[1]  George W. Irwin,et al.  Computational Intelligence and Bioinformatics, International Conference on Intelligent Computing, ICIC 2006, Kunming, China, August 16-19, 2006. Proceedings, Part III , 2006, ICIC.

[2]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[3]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[4]  Chia-Feng Juang,et al.  A hybrid of genetic algorithm and particle swarm optimization for recurrent network design , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  Xiao-Feng Xie,et al.  DEPSO: hybrid particle swarm with differential evolution operator , 2003, SMC'03 Conference Proceedings. 2003 IEEE International Conference on Systems, Man and Cybernetics. Conference Theme - System Security and Assurance (Cat. No.03CH37483).

[6]  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).

[7]  James Kennedy,et al.  Small worlds and mega-minds: effects of neighborhood topology on particle swarm performance , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[8]  J R Saunders,et al.  A particle swarm optimizer with passive congregation. , 2004, Bio Systems.

[9]  Russell C. Eberhart,et al.  Multiobjective optimization using dynamic neighborhood particle swarm optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[10]  Ben Niu,et al.  A Novel Particle Swarm Optimizer Using Optimal Foraging Theory , 2006, ICIC.

[11]  Ju-Jang Lee,et al.  Chaotic local search algorithm , 1996, Artificial Life and Robotics.

[12]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[13]  Q. Henry Wu,et al.  MCPSO: A multi-swarm cooperative particle swarm optimizer , 2007, Appl. Math. Comput..

[14]  Amitava Chatterjee,et al.  Nonlinear inertia weight variation for dynamic adaptation in particle swarm optimization , 2006, Comput. Oper. Res..

[15]  Chun Lu,et al.  An improved GA and a novel PSO-GA-based hybrid algorithm , 2005, Inf. Process. Lett..

[16]  J. Kennedy,et al.  Population structure and particle swarm performance , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[17]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[18]  P. Suganthan Particle swarm optimiser with neighbourhood operator , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).