Title :
Evolving neural induction regular language using combined evolutionary algorithms
Author :
Yang, Jim-Moon ; Kao, Cheng-Yan ; Horng, Jorng-Tzong
Author_Institution :
National Taiwan University
Abstract :
This paper proposes a new algorithm called combined evolutionary algorithm (CEA) to train a neural network, and demonstrates its use in inducing thefinite state automata task. This algorithm evolves neural networks by incorporating the ideas of evolutionary programming(EP) and real coded genetic algorithms (RCGA) into evolution strategies (ESs). Simultaneously, we add the local competition into the CEA in order to reduce the complexity and maintain the diversity. This algorithm is able to balance the exploration and exploitation dynamically. We implement CEA and experiment on seven benchmark problems of regular language. The results indicate that the CF-4 is a powerful technique to construct neural networks.
Keywords :
Automata; Computer science; Electronic switching systems; Equations; Evolutionary computation; Genetic algorithms; Neural networks; Recurrent neural networks; Supervised learning; Training data;
Conference_Titel :
ISAI/IFIS 1996. Mexico-USA Collaboration in Intelligent Systems Technologies. Proceedings
Conference_Location :
IEEE
Print_ISBN :
968-29-9437-3