An alternative approach for neural network evolution with a genetic algorithm: Crossover by combinatorial optimization

Neural Networks

Volumn 19, Issue 4, 2006, Pages 514-528

  García Pedrajas, Nicolás ^a   Ortiz Boyer, Domingo ^a   Hervás Martínez, César ^a  

^a UNIVERSITY OF CÓRDOBA   (Spain)

Author keywords

Crossover operator; Genetic algorithms; Neural network evolution

Indexed keywords

COMBINATORIAL MATHEMATICS; MATHEMATICAL OPERATORS; NEURAL NETWORKS; OPTIMIZATION; PROBLEM SOLVING;

CROSSOVER OPERATOR; NEAR-OPTIMAL PROJECTIONS; NEURAL NETWORK EVOLUTION;

GENETIC ALGORITHMS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER PROGRAM; GENETIC ALGORITHM; GENETIC CODE; GENOTYPE; MATHEMATICAL COMPUTING; MATING; PRIORITY JOURNAL;

ALGORITHMS; ANIMALS; COMPUTER SIMULATION; CROSS-OVER STUDIES; EVOLUTION; GENETICS; HUMANS; NERVE NET; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS;

EID: 33744909840     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2005.08.014     Document Type: Article

References (50)

1. Angeline P.J., Saunders G.M., and Pollack J.B. An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 5 1 (1994) 54-65
2. Bäck T. Evolutionary algorithms in theory and practice (1996), Oxford University Press, New York, NY
3. Balakrishnan, K., & Honavar, V. (1995). Evolutionary design of neural architectures-a pleliminary taxonomy and guide to literature, technical report CS TR#95-01. Artificial Intelligence Research Group, Department of Computer Science, Iowa State University, Ames, Iowa 50011-1040, USA (January 1995).
4. Branke J. Evolutionary algorithms for neural network design and training. In: Talander J. (Ed). Proceeding of the first nordic workshop on genetic algorithms and its applications, Vaasa, Finland, 1995 (1995)
5. Cantú-Paz E., and Kamath C. Evolving neural networks to identify bent-double galaxies in the first survey. Neural Networks 16 (2003) 507-517
6. Caruana R., Lawrence S., and Giles L. Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping. In: Leen T.K., Dietterich T.G., and Tresp V. (Eds). Advances in neural information processing systems 13. Papers from neural information processing systems (NIPS) 2000 (2001), MIT Press, Denver, CO 402-408
7. Delahaye D., and Odoni A. Airspace congestion smoothing by stochastic optimization. In: Angeline P.J. (Ed). Conference on evolutionary programming '97 (1997), Springer, Indianapolis, IN
8. Denison D.G.T., Holmes C.C., Mallick B.K., and Smith A.F.M. Bayesian methods for nonlinear classification and regression. Wiley series in probability and statistics (2002), Wiley, West Sussex, England
9. Dorigo M., Maniezzo V., and Colorni A. The ant system: Optimization by a colony of cooperating agents. IEEE Transactions on Systems, Man, and Cybernetics-Part B 26 1 (1996) 1-13
10. Eshelman L.J. The CHC adaptive search algorithm: How to have safe search when engaging in nontraditional genetic recombination (1990), Morgan Kauffman, San Mateo, CA
11. Floreano D., and Urzelai J. Evolutionary robots with on-line self-organization and behavioral fitness. Neural Networks 13 (2000) 431-443
12. García-Pedrajas N., Hervás-Martínez C., and Muñoz-Pérez J. Multiobjective cooperative coevolution of artificial neural networks. Neural Networks 15 10 (2002) 1255-1274
13. García-Pedrajas N., Hervás-Martínez C., and Muñoz-Pérez J. Covnet: A cooperative coevolutionary model for evolving artificial neural networks. IEEE Transactions on Neural Networks 14 3 (2003) 575-596
14. Goldberg D.E. Genetic algorithms in search, optimization and machine learning (1989), Addison-Wesley, Reading, MA
15. Goldberg D.E. Genetic algorithms and Walsh functions: Part 2, deception and its analysis. Complex Systems 3 (1989) 153-171
16. Goldberg D.E. Genetic algorithms and Walsh functions: Part 1, a gentle introduction. Complex Systems 3 (1989) 129-152
17. Hajek B. Cooling schedules for optimal annealing. Mathematics of Operations Research 13 (1988) 311-329
18. Hassibi, B., & Stork, D. (1993). Second order derivatives for network pruning: Optimal brain surgeon. In Advances in neural information systems (Vol. 5).
19. Haykin S. Neural networks-A comprehensive foundation. 2nd ed. (1999), Prentice-Hall, Upper Saddle River, NJ
20. Hinton, G. E., & van Camp, D. (1993). Keeping neural networks simple by minimizing the description length of the weights. In Sixth ACM international conference on computational learning theory ACM, Santa Cruz, 1993 (pp. 5-13). New York, NY: ACM Press.
21. Karnin E.D. A simple procedure for pruning back-propagation trained neural networks. IEEE Transactions on Neural Networks 1 2 (1990) 239-242
22. Kennedy, J., & Eberhart, R. C. (1995). Particle swarm optimization. In IEEE international conference on neural networks. Perth, Australia: IEEE Service Center.
23. Kirkpatrick, S., Gelatt Jr., C.D., & Vecchi, M.P. (1983). Optimization by simulated annealing Science, 220, 671-680.
24. Lawrence, S., Giles, C. L., & Tsoi, A. C. What size neural network gives optimal generalization? Convergence properties of backpropagation, technical report. Institute for Advanced Computer Studies, University of Maryland (August 1996).
25. Le Cun Y., Denker J.S., and Solla S.A. Solla, optimal brain damage. In: Touretzky D.S. (Ed). Advances in neural information processing (2) (1990), Morgan Kaufmann, Denver, CO 598-605
26. Le Cun, Y. (1993). Efficient learning and second-order methods, a tutorial. In Advances in neural information processing, Denver, CO (Vol. 6).
27. Lerner B., Guterman H., Aladjem M., and Dinstein I. A comparative study of neural networks based feature extraction paradigms. Pattern Recognition Letters 20 1 (1999) 7-14
28. Louis S.J., and Li G. Combining robot control strategies using genetic algorithms with memory. Lecture Notes in Computer Science, Evolutionary Programming VI 1213 (1997) 431-442
29. Maniezzo V. Genetic evolution of the topology and weight distribution of neural networks. IEEE Transactions on Neural Networks 5 1 (1994) 39-53
30. Michalewicz Z. Genetic algorithms+data structures=evolution programs (1994), Springer, New York
31. Miller G.F., Todd P.M., and Hedge S.U. Designing neural networks. Neural Networks 4 (1991) 53-60
32. Moriarty D.E., and Miikkulainen R. Efficient reinforcement learning through symbiotic evolution. Machine Learning 22 (1996) 11-32
33. Moriarty D.E., and Miikkulainen R. Forming neural networks through efficient and adaptive coevolution. Evolutionary Computation 4 5 (1997) 373-399
34. Mozer M.C., and Smolensky P. Skeletonization: A technique for trimming the fat from a network via relevance assessment. In: Touretzky D.S. (Ed). Advances in neural information processing (1) (1989), Morgan Kaufmann, Denver, CO 107-155
35. Odri S.V., Petrovacki D.P., and Krstonosic G.A. Evolutional development of a multilevel neural network. Neural Networks 6 (1993) 583-595
36. Pujol J.C.F., and Poli R. Evolving the topology and the weights of neural networks using a dual representation. Applied Intelligence 8 1 (1998) 73-84
37. Schaffer J.D., Whitley L.D., and Eshelman L.J. Combinations of genetic algorithms and neural networks: A survey of the state of the art. In: Whitley L.D., and Schaffer J.D. (Eds). Proceedings of COGANN-92 international workshop on combinations of genetic algorithms and neural networks (1992), IEEE Computer Society Press, Los Alamitos, CA 1-37
38. Setiono R. A penalty-function approach for pruning feedforward neural networks. Neural Computation 9 (1997) 185-204
39. Setiono R. Feedforward neural network construction using cross validation. Neural Computation 13 (2001) 2865-2877
40. Smalz R., and Conrad M. Combining evolution with credit apportionment: A new learning algorithm for neural nets. Neural Networks 7 2 (1994) 341-351
41. Thierens, D. (1996). Non-redundant genetic coding of neural networks. In Proceeding of the 1996 IEEE international conference on evolutionary computation (pp. 571-575). Piscataway, NJ: IEEE Press.
42. Thierens, D., Suykens, J., Vandewalle, J., & Moor, B. D. (1991). Genetic weight optimization of a feedforward neural network controller. In Proceedings of the conference on neural nets and genetic algorithms (pp. 658-663). Berlin: Springer.
43. Treadgold N.K., and Gedeon T.D. Exploring constructive cascade networks. IEEE Transactions on Neural Networks 10 6 (1999) 1335-1350
44. van Rooij A.J.F., Jain L.C., and Johnson R.P. Neural networks training using genetic algorithms. Machine perception and artificial intelligence Vol. 26 (1996), World Scientific, Singapore
45. Weigend A.S. On overfitting and the effective number of hidden units. In: Mozer M.C., Smolensky P., Touretzky D.S., Elman J.L., and Weigend A.S. (Eds). Proceedings of the 1993 connectionist models summer school (1993), Erlbaum Associates, Hillsdale, NJ 335-342
46. Weigend A.S. On overfitting and the effective number of hidden units. In: Mozer M.C., Smolensky P., Touretzky D.S., Elmand J.L., and Weigend A.S. (Eds). Proceedings of the 1993 connectionist models summer school (1994), Erlbaum Associates, Hillside, NJ 335-342
47. Whitehead B.A., and Choate T.D. Cooperative-competitive genetic evolution of radial basis function centers and widths for time series prediction. IEEE Transactions on Neural Networks 7 4 (1996) 869-880
48. Yang, J., Parekh, R., & Honavar, V. DistAI: An inter-pattern distance-based constructive learning algorithm, technical report TR #97-05. Artificial Intelligence Research Group, Department of Computer Science, Iowa State University, Ames, Iowa (February 1997).
49. Yao X. Evolving artificial neural networks. Proceedings of the IEEE 9 87 (1999) 1423-1447
50. Yao X., and Liu Y. A new evolutionary system for evolving artificial neural networks. IEEE Transactions on Neural Networks 8 3 (1997) 694-713