Evolution Strategy with Neighborhood Attraction -A Robust Evolution Strategy

摘要

The evolution strategy with neighborhood attraction (EN) is a new combination of self-organizing maps (SOM) and evolution strategies (ES). It adapts the neighborhood relationship known from SOM to ES individuals in order to concentrate them around the optimum of the problem. In this paper, detailed investigations on the robustness of the EN were performed on a variety of well-known optimization problems. The behavior of the EN was compared to that of several other known variants of ES such as ES with mutative step control, ES with co-variance matrix adaptation, differential evolution and others. In this test series, it was shown that EN is much more robust than the other ES variants.