Adaptive Evolutionary Optimization of Team Work
Disordered Systems and Neural Networks
2007-05-23 v1
Abstract
We discuss a new optimization strategy, which considerably improves the effectivity of evolutionary algorithms applied to a certain class of optimization problems. The basic principle is to solve first a simpler related problem, which is constructed by introducing additional degrees of freedom to the landscape. Starting from the solution in this simplified landscape we remove stepwise the added degrees of freedom. Our optimization strategy is demonstrated for a sample problem.
Cite
@article{arxiv.cond-mat/0203412,
title = {Adaptive Evolutionary Optimization of Team Work},
author = {Volkhard Buchholtz and Thorsten Poeschel},
journal= {arXiv preprint arXiv:cond-mat/0203412},
year = {2007}
}
Comments
7 pages, 6 figures