Top > JACIII > Evolution and Learning Mediated by Differences in Developmenta ...

single-jc.php

JACIII Vol.11 No.8 pp. 905-913
doi: 10.20965/jaciii.2007.p0905
(2007)

Paper:

Views over last 60 days: 432

Evolution and Learning Mediated by Differences in Developmental Timing

Kei Ohnishi*, Masato Uchida**, and Yuji Oie***

*Human Media Creation Center / Kyushu, 3-8-1 Asano, Kokura-Kita-ku, Kitakyushu, Fukuoka 802-0001, JAPAN

**Network Design Research Center, Kyushu Institute of Technology, 3-8-1 Asano, Kokura-Kita-ku, Kitakyushu, Fukuoka 802-0001, JAPAN

***Faculty of Computer Science and Systems Engineering, Kyushu Institute of Technology, 680-4 Kawazu, Iizuka, Fukuoka 820-8502, JAPAN

Received:
March 12, 2007
Accepted:
June 7, 2007
Published:
October 20, 2007
Creative Commons License
Keywords:
evolutionary algorithm, developmental timing, genotype-phenotype-mapping, sequential convergence, network topology
Abstract
The present paper introduces a mutation-based evolutionary algorithm that evolves genes to regulate the developmental timings of phenotypic values. For each generation, an individual in the evolutionary algorithm time-sequentially generates a given number of entire phenotypes before finishing its life. Each gene represents a cycle time of changing probability for determining its corresponding phenotypic value, which is an indicator of developmental timing. In addition, the algorithm has a learning mechanism such that, during the lifetime of an individual, genes representing a long cycle time can change the probability of adaptation more easily than genes representing a short cycle time. Therefore, if the diversity of the genes is maintained, it can be expected that the algorithm provides a different evolution speed to each phenotypic value. The present paper also discusses a new approach to depicting an evolutionary optimization process. An evolutionary optimization process involves the identification of linkage between variables, and therefore, network structures formed using the identified linkage information determine how the evolutionary algorithm solves a given optimization problem. The proposed approach regards an evolutionary optimization process as a change in the network topology that emerges in the process of linkage identification. The simulation results indicate that evolution and learning mediated by the difference in developmental timing helps to sequentially solve hard uniformly-scaled bit optimization problems with linkage between variables.
Cite this article as:
K. Ohnishi, M. Uchida, and Y. Oie, “Evolution and Learning Mediated by Differences in Developmental Timing,” J. Adv. Comput. Intell. Intell. Inform., Vol.11 No.8, pp. 905-913, 2007.
Data files:
References
  1. [1] A. Cangelosi, “Heterochrony and Adaptation in Developing Neural Networks,” Proc. of the Genetic and Evolutionary Computation Conference 1999, San Francisco, CA, pp. 1241-1248, 1999.
  2. [2] K. Deb and D. E. Goldberg, “Analyzing Deception in Trap Functions,” Foundations of Genetic Algorithms, Vol.2, pp. 93-108, 1993.
  3. [3] D. E. Goldberg, B. Korb, and K. Deb, “Messy Genetic Algorithms: Motivation, Analysis, and First Results,” Complex Systems, Vol.3, No.5, pp. 493-530, 1989.
  4. [4] S. J. Gould, “Ontogeny and Phylogeny,” Harvard Univ. Press, Oxford, 1977.
  5. [5] G. R. Harik and D. E. Goldberg, “Learning Linkage,” Foundations of Genetic Algorithms, Vol.4, pp. 247-262, 1996.
  6. [6] H. Kitano, “Designing Neural Networks Using Genetic Algorithms with Graph Generation System,” Complex Systems, Vol.4, No.4, pp. 461-476, 1990.
  7. [7] P. Larranaga and J. A. Lozano, “Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation, Kluwer Academic Publishers, 2001.
  8. [8] K. Ohnishi, K. Sastry, Y.-P. Chen, and D. E. Goldberg, “Inducing Sequentiality Using Grammatical Genetic Codes,” Proc. of the Genetic and Evolutionary Computation Conference 2004, Seattle, WA, pp. 1426-1437, 2004.
  9. [9] M. Pelikan, D. E. Goldberg, and F. Lobo, “A Survey of Optimization by Building and Using Probabilistic Models,” IlliGAL Report No.99018, Illinois Genetic Algorithms Lab., Univ. of Illinois, Urbana, IL, 1999.
  10. [10] C. Ryan, J. J. Collins, and M. O’Neill, “Grammatical Evolution : Evolving Programs for an Arbitrary Language,” Proc. of the First European Conference on Genetic Programming, pp. 83-96, 1998.
  11. [11] C. Ryan, M. Nicolau, and M. O’Neill, “Genetic Algorithms Using Grammatical Evolution,” Proc. of the Fifth European Conference on Genetic Programming (EuroGP 2002), pp. 278-287, 2002.
  12. [12] H. Satoh, M. Yamamura, and S. Kobayashi, “Minimal Generation Gap Model for GAs Considering Both Exploration and Exploitation,” Proc. of the Int. Conf. on Fuzzy Systems, Neural Networks and Soft Computing (Iizuka’96), pp. 494-497, 1996.
  13. [13] G. Syswerda, “A Study of Reproduction in Generational and Steady State Genetic Algorithms,” Foundations of Genetic Algorithms, Morgan Kaufmann, San Mateo, CA, pp. 94-101, 1991.
  14. [14] D. Thierens and D. E. Goldberg, “Mixing in Genetic Algorithms,” Proc. of the 5th Int. Conf. on Genetic Algorithms (ICGA-93), pp. 38-45, 1993.

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Apr. 18, 2024