Abstract
Using evolutionary simulations, we develop autonomous agents controlled by artificial neural networks (ANNs). In simple life-like tasks of foraging and navigation, high performance levels are attained by agents equipped with fully-recurrent ANN controllers. Examining several experimental settings, differing in the sensory input available to the agents, we find a common structure of a “command neuron” switching the dynamics of the network between radically different behavioural modes. In some of the models the command neuron reflects a map of the environment, acting as a “place cell”. In others it is based on a spontaneously evolving short-term memory mechanism. The resemblance to known findings from neurobiology places Evolved ANNs as an excellent candidate model for the study of structure and function relation in complex nervous systems.
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
D. Amit. Modeling Brain Function. Cambridge University Press, New York, 1989.
A. Cangelosi, D. Parisi, and S. Nolfi. Cell division and migration in a ‘genotype’ for neural networks. Network, (5):497–515, 1994.
D. Floreano and F. Mondada. Evolution of homing navigation in a real mobile robot. IEEE Transactions on Systems, Man, and Cybernetics-Part B, 26(3):396–407, June 1996.
D. B. Fogel. Evolutionary Computation-Toward a New Philosophy of Machine Intelligence. IEEE Press, Piscataway, NJ, 1995.
P. G. Harrald and M. Kamstra. Evolving artificial neural networks to combine financial forecasts. IEEE Transactions on Evolutionary Computation, 1(1):40–52, April 1997.
J. Hertz, A. Krogh, and R. Palmer. Introduction to the Theory of Neural Computation. Addison-Wesley Publishing Company, New York, 1991.
N. Jakobi. Evolutionary robotics and the radical envelope-of-noise hypothesis. Adaptive Behavior, 6(2):325–368, 1998.
H. Kitano. Designing neural networks using genetic algorithms with graph generation system. Complex Systems, (4):461–76, 1990.
P. D. Martin and J. O’Keefe. Place field dynamics and directionality in a spatial memory task. Brain Research, 783(2):249–261, February 1998.
M. Mitchell. An Introduction to Genetic Algorithms. The MIT Press, Cambridge, Massachusetts, 1996.
C. Scheier, R. Pfeifer, and Y. Kunyioshi. Embedded neural networks: Exploiting constraints. Neural Networks, (7–8):1551–1569, October–November 1998.
T. Teyke, K. R. Weiss, and I. Kupfermann. An ientified neuron (CPR) evokes neuronal responses reflecting food arousal in aplysia. Science, (247):85–87, January 1990.
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
Aharonov-Barki, R., Beker, T., Ruppin, E. (1999). Spontaneous Evolution of Command Neurons, Place Cells and Memory Mechanisms in Autonomous Agents. 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_31
Download citation
DOI: https://doi.org/10.1007/3-540-48304-7_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66452-9
Online ISBN: 978-3-540-48304-5
eBook Packages: Springer Book Archive