Artificial Neural Network Weights Optimization based on Imperialist Competitive Algorithm

Imperialist Competitive Algorithm (ICA) is a new sociopolitically motivated global search strategy that has recently been introduced for dealing with different optimization tasks In this paper, we adopt ICA to optimize the weights of Multilayer Perceptron (MLP) Artificial Neural Network to solve premature convergence problem of Genetic Algorithm and some other similar algorithms. For this purpose, ICA is applied on four known datasets (WINE, GLASS, PIMA, WDBC) which are used for classification problems and compared with three other training methods. In almost all datasets, the proposed method outperforms its competitors.

[1]  Caro Lucas,et al.  Imperialist competitive algorithm: An algorithm for optimization inspired by imperialistic competition , 2007, 2007 IEEE Congress on Evolutionary Computation.

[2]  A. Yamazaki,et al.  Optimization of neural network weights and architectures for odor recognition using simulated annealing , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[3]  Jing Jie,et al.  Artificial neural network weights optimization design based on MEC algorithm , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[4]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[5]  Zhaocai Xi,et al.  The Research on BP Neural Network Model Based on Guaranteed Convergence Particle Swarm Optimization , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[6]  Caro Lucas,et al.  Imperialist competitive algorithm for minimum bit error rate beamforming , 2009, Int. J. Bio Inspired Comput..

[7]  Sung-Bae Cho,et al.  Evolutionary neural networks for anomaly detection based on the behavior of a program , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Caro Lucas,et al.  Colonial competitive algorithm: A novel approach for PID controller design in MIMO distillation column process , 2008, Int. J. Intell. Comput. Cybern..

[9]  Xilong Qu,et al.  Parallel Genetic Algorithm Model Based on AHP and Neural Networks for Enterprise Comprehensive Business , 2008, 2008 International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[10]  Caro Lucas,et al.  Colonial Competitive Algorithm as a Tool for Nash Equilibrium Point Achievement , 2008, ICCSA.

[11]  Isaac E. Lagaris,et al.  Program Summary , 1986, PMLA/Publications of the Modern Language Association of America.

[12]  Euripidis Glavas,et al.  Neural network construction and training using grammatical evolution , 2008, Neurocomputing.

[13]  Caro Lucas,et al.  Vehicle Fuzzy Controller Design Using Imperialist Competitive Algorithm , 2008 .

[14]  Juan Julián Merelo Guervós,et al.  Evolving RBF neural networks for time-series forecasting with EvRBF , 2004, Inf. Sci..

[15]  A AbbassHussein.  An evolutionary artificial neural networks approach for breast cancer diagnosis , 2002 .

[16]  Hussein A. Abbass,et al.  An evolutionary artificial neural networks approach for breast cancer diagnosis , 2002, Artif. Intell. Medicine.