Evolutionary algorithms for real-time artificial neural network training.
Jagadeesan, Ananda Prasanna
Maxwell, Grant M.
MetadataShow full item record
JAGADEESAN, A., MAXWELL, G. and MACLEOD, C. 2005. Evolutionary algorithms for real-time artificial neural network training. Lecture notes in computer science [online], 3697, Proceedings of the 15th international conference on artifical neural networks (ICANN 2005): formal models and their applications, 11-15 September 2005, Warsaw, Poland, part 2, pages 73-78. Available from: https://dx.doi.org/10.1007/11550907_12
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.