Abstract
A system for generating neural networks to control simulated agents is described. The networks develop during the lifetime of the agents in a process guided by the genotype and affected by the agent’s experience. Evolution was used to generate effective controllers of this kind for orientation and discrimination tasks as introduced by Beer. This scheme allows these behaviours to be generated quickly and effectively and may offer insights into the effects of developmental processes on cognition. For example, development may allow environmental regularities to be recognised without genetic prespecification. Possible future research into the abilities of these controllers to adapt to radical changes and to undertake widely varying tasks with a single genotype is described.
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
Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: SAB4 (1996)
Di Paolo, E.A.: Homeostatic adaptation to inversion of the visual field and other sensorimotor disruptions. In: Proc. of SAB 2000 (2000)
Elliot, T., Shadbolt, N.: Growth and repair: Instantiating a biologically inspired model of neuronal development on the Khepera robot. Robotics and Autonomous Systems 36, 149–169 (2001)
Elman, J.: Learning and development in neural networks: The importance of starting small. Cognition 48, 71–99 (1993)
Floreano, D., Mondada, F.: Evolution of plastic neurocontrollers for situated agent. In: SAB4 (1996)
Floreano, D., Mondada, F.: Evolutionary neurocontrollers for autonomous mobile robots. Neural Networks 11, 1461–1478 (1998)
Gruau, F., Whitley, D.: Adding learning to the cellular development of neural networks: Evolution and the Baldwin effect. Evolutionary Computation 1, 213–234 (1993)
Gruau, F.: Neural Network Synthesis Using Cellular Encoding and the Genetic Algorithm PhD. Thesis, Ecole Normale Superieure de Lyon, LPIMAG (1994)
Gruau, F.: Automatic Definition of Modular Neural Networks. Adaptive Behaviour 3(2), 151–183 (1995)
Held, R.: Plasticity in sensory-motor systems. Scientific American 213(5), 84–94 (1965)
Ivanco, T., Greenough, W.: Physiological consequences of morphologically detectable synaptic plasticity: potential uses for examining recovery following damage. Neuropharmacology 39, 765–776 (2000)
Jakobi, N.: Harnessing Morphogenesis Technical Report School of Cognitive and Computing Sciences, University of Sussex (1995)
Karmiloff-Smith, A.: Beyond Modularity: A Developmental Perspective on Cognitive Science. MIT Press, Cambridge (1992)
Kolb, B., Forgie, M., Gibb, R., Gorny, G., Rowntree, S.: Age, Experience and the Changing Brain. Neuroscience and Biobehavioural Reviews 22(2), 143–159 (1998)
Nolfi, S., Miglino, O., Parisi, D.: Phenotypic plasticity in evolving neural networks. In: Proceedings of the International Conference From Perception to Action pp. 146–157 (1994)
Quartz, S., Sejnowski, T.: The neural basis of cognitive development: a constructivist manifesto. Behavioural and Brain Sciences 20, 537–596 (1997)
Quartz, S.: The constructivist brain. Trends in Cognitive Sciences 3(2), 48–57 (1999)
Quinlan, P.: Structural change and development in real and artificial neural networks. Neural Networks 11, 577–599 (1998)
Slocum, A., Downey, D., Beer, R.: Further Experiments in the Evolution of Minimally Cognitive Behaviour. In: SAB6 (2000)
van Praag, H., et al.: Functional neurogenesis in the adult hippocampus. Nature 415, 1030–1034 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Balaam, A. (2003). Developmental Neural Networks for Agents. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds) Advances in Artificial Life. ECAL 2003. Lecture Notes in Computer Science(), vol 2801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39432-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-39432-7_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20057-4
Online ISBN: 978-3-540-39432-7
eBook Packages: Springer Book Archive