Abstract
The relationship between evolution (genetic & developmental processes of an evolutionary system) and modularity (its support for modular structures) is explored. Modules are defined as structures with common origin; either evolutional or developmental. In the former case, processes supporting modularity operate on the phylogenetic level, in the latter, on the ontogenetic level. Three such processes are identified (duplication, divergence, covergence). The existence of these processes determine the system’s support for modularity. Modules are analysed in the particular context of artificial neural networks (ANNs), where they appear as subnetworks. Gruau’s cellular developmental encoding is used as an example, and an extension is proposed which better supports modularity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Calabretta, R., et. al. A case study of the evolution of modularity: towards a bridge between evolutionary biology, artificial life, neuro-and cognitive science. In Proceedings of “Artificial Life VI”, 1998. Adami, C. et al., eds., MIT Press, 1998.
Gilbert, S. Developmental Biology. Sinauer Associates, Sunderland, MA, 1991.
Grönroos, M. A. Evolutionary Design of Neural Networks. M. Sc. thesis, Computer Science, Department of Mathematical Studies, University of Turku, 1998.
Gruau, F., Whitley, D. L. Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. In J. of Evolutionary Computation, 1(3):213–233. 1993.
Gruau, F. Modular Genetic Neural Networks for 6-Legged Locomotion. In Artificial Evolution European Conference, 1995. Lecture Notes in Computer Science, Alliot, J.-M., Lutton, E., Ronald, E., Schoenauer, M., Snyers, D., eds., Springer, Berlin, 1996. 201–219.
Gruau, F., Quatramaran, K. Cellular Encoding for Interactive Evolutionary Robotics. Research report 425, Univ. of Sussex, School of Cognitive and Computing Sciences, 1996.
Hadley, R. F. Connectionism and Novel Combination of Skills: Implications for Cognitive Architecture. Technical Report CMPT TR 1998-01, Simon Fraser University, 1998.
Michel, O., Collard, Ph. Artificial neurogenesis: an application to autonomous robotics. In Proceedings of the 8th International Conference on Tools with Artificial Intelligence, Radle, M. G., ed., IEEE Computer Society Press, 1996. 207–214.
Ray, T. S. Selecting Naturally for Differentiation: preliminary evolutionary results. In Complexity, 3(5): 25–33. John Wiley & Sons Inc., 1998.
Whitley, D. L., Gruau, F., Pyeatt, L. Cellular Encoding Applied to Neurocontrol. In 6th Inttl. Conference on Genetic Algorithms, Eshelmann, L., ed., Morgan Kaufmann, 1995.
Sanchez, E., Mange, D., Sipper, M., Tomassini, M., Pérez-Uribe, A., Stauffer, A. Phylogeny, ontogeny, and epigenesis: Three sources of biological inspiration for softening hardware. In Proceedings of The First Intl. Conference on Evolvable Systems: From Biology to Hardware (ICES96), vol. 1259 of LNCS, Higuchi, T., et al., eds., Springer-Verlag, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rotaru-Varga, Á. (1999). Modularity in Evolved Artificial Neural Networks. In: Floreano, D., Nicoud, JD., Mondada, F. (eds) Advances in Artificial Life. ECAL 1999. Lecture Notes in Computer Science(), vol 1674. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48304-7_32
Download citation
DOI: https://doi.org/10.1007/3-540-48304-7_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66452-9
Online ISBN: 978-3-540-48304-5
eBook Packages: Springer Book Archive