Evolutionary algorithms for real-time artificial neural network training.

Jagadeesan, Ananda; Maxwell, Grant; MacLeod, Christopher

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.

Citation

JAGADEESAN, A., MAXWELL, G. and MACLEOD, C. 2005. Evolutionary algorithms for real-time artificial neural network training. In Duch, W., Kacprzyk, J., Oja, E. and Zadrozy, S (eds.) Artificial neural networks: formal models and their applications, part 2; proceedings of the 15th International on artificial neural networks (ICAAN 2005), 11-15 September 2005, Warsaw, Poland. Lecture notes in computer science, 3697. Berlin: Springer, pages 73-78. Available from: https://dx.doi.org/10.1007/11550907_12

• Conference Name: 15th International conference on artificial neural networks (ICAAN 2005): formal models and their applications
• Conference Location: Warsaw, Poland
• Start Date: Sep 11, 2005
• End Date: Sep 15, 2005
• Acceptance Date: Sep 11, 2005
• Online Publication Date: Dec 31, 2005
• Publication Date: Dec 31, 2005
• Deposit Date: Sep 16, 2016
• Publicly Available Date: Sep 16, 2016
• Print ISSN: 0302-9743
• Publisher: Springer
• Pages: 73-78
• Series Title: Lecture notes in computer science
• Series Number: 3697
• Series ISSN: 0302-9743
• ISBN: 9783540287551
• DOI: https://doi.org/10.1007/11550907_12
• Keywords: Evolutionary algorithms; Artificial neural networks; Robotics
• Public URL: http://hdl.handle.net/10059/1728