Abstract
This paper reports on experiments investigating the use of Evolutionary Algorithms to train Artificial Neural Networks in real time. A simulated legged mobile robot was used as a test bed in the experiments. Since the algorithm is designed to be used with a physical robot, the population size was one and the recombination operator was not used. The algorithm is therefore rather similar to the original Evolutionary Strategies concept. The idea is that such an algorithm could eventually be used to alter the locomotive performance of the robot on different terrain types. Results are presented showing the effect of various algorithm parameters on system performance.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Carpenter, G.A., Grossberg, S.: ART - 2: self organisation of stable category recognition codes for analog input patterns. Applied Optics 26, 4919–4930 (1987)
Muthuraman, S., Maxwell, G.M., MacLeod, C.: The Evolution of Modular Artificial Neural Networks for Legged Robot Control. In: Proceedings of the International Conference on Neural Networks and Neural Information Processing (ICANN/ICONIP 2003), Istanbul (Turkey), June 2003, pp. 488–495 (2003)
McMinn, D., MacLeod, C., Maxwell, G.M.: Evolutionary Artificial Neural Networks for Quadruped Locomotion. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 789–794. Springer, Heidelberg (2002)
Schwefel, H.-P.: Evolution and Optimum Seeking. Wiley, New York (1995)
Yip, P.P.C., Pao, Y.: Growing Neural Networks using Guided Evolutionary Simulated Annealing. In: Proceedings of the International Conference on Evolutionary Programming, Istanbul (Turkey), June 1994, pp. 17–20 (1994)
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
Jagadeesan, A., Maxwell, G., MacLeod, C. (2005). Evolutionary Algorithms for Real-Time Artificial Neural Network Training. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_12
Download citation
DOI: https://doi.org/10.1007/11550907_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)