Genetic algorithms with sharing for multimodal function optimization
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Niching methods for genetic algorithms
Niching methods for genetic algorithms
The nature of niching: genetic algorithms and the evolution of optimal, cooperative populations
The nature of niching: genetic algorithms and the evolution of optimal, cooperative populations
Implicit niching in a learning classifier system: Nature's way
Evolutionary Computation
Basic principles for understanding evolutionary algorithms
Fundamenta Informaticae
Shape nesting by coevolving species
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Optimal nesting of species for exact cover of resources: two against many
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Optimal Nesting of Species for Exact Cover: Many against Many
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
Basic principles for understanding evolutionary algorithms
Fundamenta Informaticae
NP-completeness and the coevolution of exact set covers
Proceedings of the 15th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
This paper introduces a new algorithm for sharing to induce niching and speciation. Resource-based fitness sharing is a compromise between the very natural method of resource sharing and the practical technique of fitness sharing. Fitness sharing was meant to simulate resource sharing for function optimization problems, in which there are no explicit resources to share. Fitness sharing therefore cannot resolve resource-defined niches as can resource sharing. However, selection operators seem to have great difficulty handling the non-linear interactions among shared fitnesses under "natural resource sharing". To obtain the benefits of both methods, we propose a sharing function that utilizes actual resources but in a form similar to that of fitness sharing, resulting in a set of linear equations for equilibrium, and hence much simpler dynamics under selection. The superiority of this compromise is demonstrated on a resource-coverage problem.