Abstract
We introduce an artificial neural network (ANN) representation that supports the evolution of complex behaviors in artificial organisms. The strength and location of each connection in the network is specified by a connection descriptor. The connection descriptors are mapped directly into a bit-string to which a genetic algorithm is applied. We empirically compare this representation to other ANN-based representations in the complex AntFarm task.
Preview
Unable to display preview. Download preview PDF.
References
Robert J. Collins and David R. Jefferson. Representations for artificial organisms. In Jean-Arcady Meyer and Stewart Wilson, editors, Proceedings, Simulation of Adaptive Behavior. The MIT Press/Bradford Books, (in press).
Robert J. Collins and David R. Jefferson. AntFarm: A progress report. In Christopher Langton, J. Doyne Farmer, Steen Rasmussen, and Charles Taylor, editors, Artificial Life II. Addison-Wesley Publishing Company, (submitted, in press).
W. Daniel Hillis. The Connection Machine. The MIT Press, Cambridge, Massachusetts, 1985.
David Jefferson, Robert Collins, Claus Cooper, Michael Dyer, Margot Flowers, Richard Korf, Charles Taylor, and Alan Wang. The Genesys System: Evolution as a theme in artificial life. In Christopher Langton, J. Doyne Farmer, Steen Rasmussen, and Charles Taylor, editors, Artificial Life II. Addison-Wesley Publishing Company, (submitted, in press).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Collins, R.J., Jefferson, D.R. (1991). An artificial neural network representation for artificial organisms. In: Schwefel, HP., Männer, R. (eds) Parallel Problem Solving from Nature. PPSN 1990. Lecture Notes in Computer Science, vol 496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0029761
Download citation
DOI: https://doi.org/10.1007/BFb0029761
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54148-6
Online ISBN: 978-3-540-70652-6
eBook Packages: Springer Book Archive