作者: Nicolás García-Pedrajas , César Hervás-Martínez , Domingo Ortiz-Boyer
关键词: Coevolution 、 Process (engineering) 、 Evolutionary computation 、 Cooperative coevolution 、 Artificial intelligence 、 Artificial neural network 、 Evolutionary programming 、 Modular design 、 Variety (cybernetics) 、 Computer science
摘要: This chapter presents a cooperative revolutionary model for evolving artificial neural networks. is based on the idea of coevolving subnetworks that must cooperate to form solution specific problem, instead complete The combination these part coevolutionary process. best combinations be evolved together with coevolution subnetworks. Several subpopulations coevolve cooperatively and genetically isolated. individuals every subpopulation are combined whole different approach from most current models evolutionary networks which try develop places as few restrictions possible over network structure, allowing reach wide variety architectures during evolution easily extensible other kind performance in solving ten real problems classification compared modular network, adaptive mixture experts, results reported literature.