Structural learning of neural networks by differential evolution with degeneration using mappings

2007 IEEE Congress on Evolutionary Computation, CEC 2007

Volumn , Issue , 2007, Pages 3434-3441

  Takahama, Tetsuyuki ^a,b   Sakai, Setsuko ^a,c   Hara, Akira ^a,b   Iwane, Noriyuki ^a,b  

^a IEEE

^b HIROSHIMA CITY UNIVERSITY   (Japan)

^c HIROSHIMA SHUDO UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

DIFFERENTIAL EVOLUTION (DE); GAUSSIAN MUTATION; STRUCTURAL LEARNING;

GAUSSIAN DISTRIBUTION; GENETIC ALGORITHMS; OPTIMIZATION; PARAMETER ESTIMATION; ROBUST CONTROL; SUPERVISED LEARNING;

NEURAL NETWORKS;

EID: 74349097501     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CEC.2007.4424916     Document Type: Conference Paper

References (27)

1. T. Kurita, "A method to determine the number of hidden units of three layered neural networks by information criteria," Transactions of the Institute of Electronics, Information and Communication Engineers, J73-D-II, vol. 11, pp. 1872-1878, 1990, in Japanese.
2. N. Murata, S. Yoshizawa, and S. Amari, "Network information criterion-determining the number of hiddenunits for an artificial neural network model," IEEE Transactions ons Neural Networks, vol. 5, no. 6, pp. 865-872, 1994.
3. H. Akaike, "A new look at the statistical model identification, " IEEE Trans. Automatic Control, vol. AC-19, no. 6, pp. 716-723, 1974.
4. J. Rissanen, "Stochastic Complexity and Modeling," The Annals of Statistics, vol. 14, no. 3, pp. 1080-1100, Sept. 1986.
5. J. Moody, "The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems," in Advances in Neural Information Processing Systems, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo: Morgan Kaufmann, 1992, vol. 4, pp. 847-854.
6. Y. L. Cun, J. S. Denker, and S. A. Solla, "Optimal brain damage," in Advances in Neural Information Processing Systems 4, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1992, pp. 598-605.
7. B. Hassibi and D. Stork, "Second Order Derivatives for Network Pruning: Optimal Brain Surgeon," in Advances in Neural Information Processing Systems, J. D. C. S. J. Hanson and C. L. Giles, Eds. San Mateo: Morgan Kaufmann Publishers Inc., 1993, vol. 5, pp. 164-171.
8. M. C. Mozer and O. Smolensky, "Using relevance to reduce network size automatically," Connection Science, vol. 1, no. 1, pp. 3-16, 1989.
9. C. Campbell, "Constructive learning techniques for designing neural network systems," in Neural Network Systems Technologies and Applications, C. T. Leondes, Ed. San Diego: Academic Press, 1997.
10. S. E. Fahlman and C. Lebiere, "The cascade-correlation learning architecture," in Advances in Neural Information Processing Systems 2, D. S. Touretzky, Ed. San Mateo, CA: Morgan Kaufmann, 1992, pp. 642-649.
11. R. Parekh, J. Yang, and V. Honavar, "Constructive neural-network learning algorithms for pattern classification," Neural Networks, IEEE Transactions on, vol. 11, no. 2, pp. 436-451, 2000.
12. M. Ishikawa, "Structural learning with forgetting," Neural Networks, vol. 9, no. 3, pp. 509-521, 1996.
13. T. Takahama and S. Sakai, "MGGA: Genetic algorithm with mutant genes," IEICE Trans. on Information and Systems, vol. J84-D-I, no. 9, pp. 1297-1306, Sept. 2001, in Japanese.
14. - , "MGGA: Genetic algorithm with mutant genes," Systems and Computers in Japan, vol. 33, no. 14, pp. 23-32, 2002.
15. - , "Structural optimization of neural network by genetic algorithm with damaged genes," in Proceedings of the 9th International Conference of Neural Information Processing(ICONIP'02), vol. 3, 2002, pp. 1211-1215
16. - , "Structural learning by genetic algorithm with damaged genes," in Proc. of the IASTED International Conference on Artificial and Computational Intelligence (ACI2002). ACTA Press, Anaheim, USA, Sept. 2002, pp. 161-166.
17. T. Takahama, S. Sakai, T. Ichimura, and Y. Isomichi, "Structural optimization by genetic algorithm with degeneration(GAd)," IEICE Trans. on Information and Systems, vol. J86-D-I, no. 3, pp. 140-149, Mar. 2003, in Japanese.
18. - , "Structural optimization by genetic algorithm with degeneration(GAd)," Systems and Computers in Japan, vol. 35, no. 5, pp. 32-43, 2004.
19. d)," in Neural Information Processing: Research and Development, J. C. Rajapakse and L. Wang, Eds. Springer, 2004, pp. 256-277.
20. T. Takahama, S. Sakai, and N. Iwane, "Learning structure of rbf-fuzzy rule bases by degeneration," in Poceedings of 2003 International Conference on Fuzzy Information Processing(FIP2003), Mar. 2003, pp. 611-616.
21. - , "Structural learning of rbf-fuzzy rule bases on information criteria and degeneration," in Proceedings of 2003 IEEE International Conference on Systems, Man, and Cybernetics(SMC2003), 2003, pp. 2581-2586.
22. J. E. Baker, "Adaptive selection methods for genetic algorithms," in Proc. of the First International Conference on Genetic Algorithms and Their Applications. Lawrence Erlbaum Associates, July 1985, pp. 101-111.
23. L. J. Eshelman and J. D. Schaffer, "Real-coded genetic algorithms and interval schemata," in Foundations of Genetic Algorithms 2, L. D. Whitley, Ed. San Mateo, CA: Morgan Kaufmann Publishers, 1993, pp. 187-202.
24. R. Storn and K. Price, "Minimizing the real functions of the ICEC'96 contest by differential evolution," in Proc. of the International Conference on Evolutionary Computation, 1996, pp. 842-844.
25. - , "Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces," Journal of Global Optimization, vol. 11, pp. 341-359, 1997.
26. A. Leonardis and H. Bischof, "An efficient mdl-based construction of rbf networks," Neural Networks, vol. 11, no. 5, pp. 963-973, 1998.
27. J. Yen and L. Wang, "Application of statistical information criteria for optimal fuzzy model construction," IEEE Trans. on Fuzzy Systems, vol. 6, no. 3, pp. 362-372, 1998.