| Evolutionary Speciation for Problem Decomposition (2007) | |||||||||||||||
Abstract | |||||||||||||||
| Modular problem decomposition is often employed to cope with complex real-world problems. An intelligent decomposition can efficiently lead to compact and general solutions but is, in most cases, the result of laborious domain analysis and engineering. Little has been done to automatically discover natural decompositions of complex problems while simultaneously solving the subproblems; usually, a decomposition architecture must be specified in advance. This paper presents the Evolutionary Speciation Genetic Programming (ESGP) framework which evolves a problem decomposition as an ensemble of species whose members collectively solve the problem. Problem decomposition emerges as a result of speciation and specialization within each species. Speciation is facilitated by the symbiotic representation of individuals. Cooperation among species emerges through coevolution. We present experiments on complex, multi-regime function approximation problems to demonstrate and analyze the basic concepts of the ESGP framework. 1 | |||||||||||||||
Publication details | |||||||||||||||
| |||||||||||||||