A. Byrski, M. Kisiel-Dorohinicki, and E. Nawarecki (Poland)
In the paper an agent-based approach to evolutionary optimisation of a neural network architecture is presented. A
concept of decentralised evolutionary computation realised
as an evolutionary multi-agent system (EMAS) may help to
avoid some of the shortcommings of classical evolutionary
optimisation techniques. General considerations are illustrated by the particular system dedicated to a problem of
time-series prediction. Selected experimental results conclude the work.