Abstract
The interaction between learning and evolution has elicited much interest particularly among researchers who use evolutionary algorithms for the optimization of neural structures. In this article, we will propose an extension of the existing models by including a developmental phase – a growth process – of the neural network. In this way, we are able to examine the dynamical interaction between genetic information and information learned during development. Several measures are proposed to quantitatively examine the benefits and the effects of such an overlap between learning and evolution. The proposed model, which is based on the recursive encoding method for structure optimization of neural networks, is applied to the problem domain of time series prediction. Furthermore, comments are made on problem domains which associate growing networks (size) during development with problems of increasing complexity.
Similar content being viewed by others
References
Bäck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, 1996.
Baldwin, J.: A new factor in evolution, American Naturalist, 30 (1896), 441–451.
Belew, R.: Evolution, learning, and culture: Computational metaphors for adaptive algorithms, Complex Systems 4 (1990), 11–49.
Belew, R.: Interposing an ontogenetic model between genetic algorithms and neural networks, In: J. Cowan (ed.), Advances in Neural Information Processing Systems, 5 (1993), 99–106.
Fontanari, J. and Meir, R.: The effect of learning on the evolution of asexual populations, Complex Systems 4 (1990), 401–414.
Geman, S. and Hwang, C.: Nonparametric maximum likelihood estimation by the method of sieves, The Annals of Statistics 10(2) (1982), 401–414.
Gierer, A.: Spatial organization and genetic information in brain development, Biological Cybernetics 59 (1988), 13–21.
Gruau, F.: Genetic synthesis of modular neural networks, In: S. Forrest (ed.), Genetic Algorithms: Proceedings of the 5th International Conferences (ICGA). San Mateo, CA, (1993) pp. 318–325.
Gruau, F.: Automatic definition of modular neural networks, Adaptive Behavior 3(2) (1995), 151–183.
Gruau, F. and Whitley, D: Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect, Evolutionary Computation 1(3) (1993), 213–233.
Hinton, G. and Nowlan, S: How learning can guide evolution, Complex Systems 1 (1987), 495–502.
Kitano, H.: Designing neural networks using genetic algorithms with graph generation system, Complex Systems 4 (1990), 461–476.
Lorenz, E.: Irregularity: A fundamental property of the atmosphere, Tellus A(36) (1984), 98–110.
Maynard-Smith, J.: When learning guides evolution, Nature 329 (1987), 761–762.
Nolfi, S., Elman, J. and Parisi, D.: Learning and evolution in neural networks, Adaptive Behavior 3(1) (1994a), 5–28.
Nolfi, S., Miglino, O. and Parisi, D.: 1994b, Phenotypic plasticity in evolving neural networks, In: D. Gaussier and J. Nicoud (eds.), Proceedings of the First International Conference From Perception to Action, (1994b) pp. 146–157.
Nolfi, S. and Parisi, D.: Learning to adapt to changing environments in evolving neural networks, Adaptive Behavior 5(1) (1997), 75–98.
Sasaki, T. and Tokoro, M.: Adaptation toward changing environments: Why Darwinism in nature?, In: P. Husbands and H. Inman (eds.), Fourth European Conference on Artificial Life, (1997) pp. 145–153.
Sendhoff, B.: Evolution of Structures – Optimization of Artificial Neural Structures for Information Processing, Aachen: Shaker Verlag, 1998, Doctoral dissertation.
Sendhoff, B. and Kreutz, M.: Evolutionary optimization of the structure of neural networks using a recursive mapping as encoding, In: G. Smith, N. Steele, and R. Albrecht (eds.), Artificial Neural Nets and Genetic Algorithms – Proceedings of the 1997 International Conference, 1998, pp. 370–374.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Sendhoff, B., Kreutz, M. A Model for the Dynamic Interaction Between Evolution and Learning. Neural Processing Letters 10, 181–193 (1999). https://doi.org/10.1023/A:1018724306675
Issue Date:
DOI: https://doi.org/10.1023/A:1018724306675