Abstract
This paper investigates evolvability of artificial neural networks within an artificial life environment. Five different structural mutations are investigated, including adaptive evolution, structure duplication, and incremental changes. The total evolvability indicator, Etotal, and the evolvability function through time, are calculated in each instance, in addition to other functional attributes of the system. The results indicate that incremental modifications to networks, and incorporating an adaptive element into the evolution process itself, significantly increases neural network evolvability within open-ended artificial life simulations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Altenberg, L.: The Evolution of Evolvability in Genetic Programming. In: Kinnear Jr., K.E. (ed.) Advances in Genetic Programming. MIT Press, Cambridge (1994)
Altenberg, L.: Genome growth and the evolution of the genotype-phenotype map. In: Banzhaf, W., Eeckman, F.H. (eds.) Evolution and Biocomputation: Computational Models of Evolution, pp. 205–259. Springer, Heidelberg (1995)
Astor, J., Adami, C.: Development and evolution of neural networks in an artificial chemistry. In: Proc. Third German Workshop on Artificial Life, pp. 15–30. Verlag Deutsch (1998)
Bedau, M.A., Packard, N.H.: Evolution of evolvability via adaptation of mutation rates. Biosystems 69(2-3), 143–162 (2003)
Ebner, M., Shackleton, M., Shipman, R.: How neutral networks influence evolvability. Complexity 7(2), 19–33 (2001)
Fogel, D.B.: Phenotypes, Genotypes, and Operators in Evolutionary Computation. In: Proceedings of the 1995 IEEE International Conference on Evolutionary Computation, pp. 193–198. IEEE Press, Perth (1995)
Glickman, M., Sycara, K.: Comparing Mechanisms for Evolving Evolvability. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 1999 Workshop Program, Orlando, Florida, USA, July 13 (1999)
Kirschner, M., Gerhart, J.: Evolvability. Proceedings of the National Academy of Sciences 95, 8420–8427 (1998)
Kumar, S., Bentley, P.J.: Implicit Evolvability: An Investigation into the Evolvability of an Embryogeny. In: A late-breaking paper in the Genetic and Evolutionary Computation Conference (GECCO 2000), Las Vegas, Nevada, USA, July 8-12 (2000)
Nolfi, S., Parisi, D.: Evolution of artificial neural networks. In: Handbook of brain theory and neural networks, 2nd edn., pp. 418–421. MIT Press, Cambridge (2002)
Ofria, C., Adami, C., Collier, T.C.: Design of Evolvable Computer Languages. IEEE Transactions on Evolutionary Computation 6, 420–424 (2002)
Schlessinger, E., Bentley, P.J., Lotto, R.B.: Evolving Visually Guided Agents in an Ambiguous Virtual World. In: To appear in the Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2005, Washington, DC, USA, June 25-29 (2005)
Smith, T.M.C., Husbands, P., Layzell, P., O’Shea, M.: Fitness Landscapes and Evolvability. Evolutionary Computation 10(1), 1–34 (2002)
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks Through Augmenting Topologies. Evolutionary Computation 10(2), 99–127 (2002)
Wagner, P.W., Altenberg, L.: Complex adaptations and the evolution of evolvability. Evolution 50, 967–976 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schlessinger, E., Bentley, P.J., Lotto, R.B. (2005). Analysing the Evolvability of Neural Network Agents Through Structural Mutations. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds) Advances in Artificial Life. ECAL 2005. Lecture Notes in Computer Science(), vol 3630. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553090_32
Download citation
DOI: https://doi.org/10.1007/11553090_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28848-0
Online ISBN: 978-3-540-31816-3
eBook Packages: Computer ScienceComputer Science (R0)