Evolving Artificial Neural Networks that Develop in Time

Although recently there has been an increasing interest in studing genetically-based development using Artificial Life models, the mapping of the genetic information into the phenotype is usually modeled as an abstract process that takes place instantaneously, i.e. before the creature starts to interact with the external world and is tested for fitness. In this paper we show that the temporal dimension of development has important consequences. By analyzing the results of simulations with temporally developing neural netwoks we found that evolution, by favouring the reproduction of organisms which are efficient at all epochs of their life, selects genotypes which dictate early maturation of functional neural structure but not of nonfunctional structure. In addition, we found that development in time forces evolution to be conservative with characters that mature in the first phases of development while it allows evolution to play more freely with characters that mature later in development. Finally, characters that mature in the first phases of development tend to be phylogenetically older than characters that mature later.

[1]  W. Barker.  Ontogeny and phylogeny. , 1980, Archives of surgery.

[2]  D. Parisi,et al.  Phenotypic plasticity in evolving neural networks , 1994, Proceedings of PerAc '94. From Perception to Action.

[3]  Ernst Mayr,et al.  Recapitulation Reinterpreted: The Somatic Program , 1994, The Quarterly Review of Biology.

[4]  G. E. G. Westermann,et al.  Ontogeny and Phytogeny , 1978 .

[5]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[6]  Ernst Haeckel,et al.  Generelle Morphologie der Organismen: Allgemeine Grundzüge der organischen Formen-Wissenschaft, mechanisch begründet durch die von Charles Darwin reformierte Descendenz-Theorie. Band 1: Allgemeine Anatomie. Band 2: Allgemeine Entwicklungsgeschichte , 1866 .

[7]  S. Kauffman.  Metabolic stability and epigenesis in randomly constructed genetic nets. , 1969, Journal of theoretical biology.

[8]  Richard K. Belew,et al.  Interposing an Ontogenetic Model Between Genetic Algorithms and Neural Networks , 1992, NIPS.

[9]  Stewart W. Wilson.  The Genetic Algorithm and Biological Development , 1987, ICGA.

[10]  David H. Ackley,et al.  Interactions between learning and evolution , 1991 .

[11]  Hiroaki Kitano,et al.  Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[12]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[13]  Frank Dellaert,et al.  Toward an evolvable model of development for autonomous agent synthesis , 1994 .

[14]  D. Parisi,et al.  Discontinuity in evolution: how different levels of organization imply preadaptation , 1996 .

[15]  D. Penny,et al.  Four Billion Years : An Essay on the Evolution of Genes and Organisms , 2022 .

[16]  Ernst Haeckel.  Generelle Morphologie der Organismen , 1866 .

[17]  A. Cangelosi,et al.  Cell division and migration in a 'genotype' for neural networks (Cell division and migration in neural networks) , 1993 .

[18]  L. Buss,et al.  The evolution of individuality , 1987 .

[19]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..