Sub-structural niching in non-stationary environments
10 December 2004Sastry, K., Abbass, H. A., Goldberg, D. E. (2004). Proceedings of the Australian Artificial Intelligence Conference. 873—885. [Full paper - PDF] [Full paper - PS].
Abstract:
-
Niching enables a genetic algorithm (GA) to maintain diversity in a population. It is particularly useful when the problem has multiple optima where the aim is to find all or as many as possible of these optima. When the fitness landscape of a problem changes overtime, the problem is called non-stationary, dynamic or time-variant problem. In these problems, niching can maintain useful solutions to respond quickly, reliably and accurately to a change in the environment. In this paper, we present a niching method that works on the problem substructures rather than the whole solution, therefore it has less space complexity than previously known niching mechanisms. We show that the method is responding accurately when environmental changes occur.
Posted in Conference Proceedings, Dynamic problem optimization, Estimation of Distribution Algorithms, Publications |
Trackback |
Top Of Page
Related Posts:
- Sub-structural niching in estimation of distribution algorithms
- Oiling the wheels of change: The role of adaptive automatic problem decomposition in non-stationary environments
- Substructrual surrogates for learning decomposable classification problems: Implementation and first results
- Single and Multiobjective Genetic Algorithm Toolbox in C++
- Single and multiobjective genetic algorithm toolbox for Matlab in C++
Comments are closed.
