Genetic Network Programming for Automatic Program Generation
Shingo Mabu*, Kotaro Hirasawa*, Yuko Matsuya**, and Jinglu Hu*
*Graduate School of Information, Production and Systems, Waseda University, 2-7 Hibikino, Kitakyushu, Fukuoka 808-0135, Japan
**Graduate School of Information Science and Electrical Engineering, Kyushu University, 6-10-1 Hakozaki, Higashi-ku, Fukuoka 812-8581, Japan
Received:September 23, 2004Accepted:February 11, 2005Published:July 20, 2005
Keywords:evolutionary computation, genetic network programming, memory architecture, even-n-parity problem, mirror symmetry problem
In this paper, a recently proposed Evolutionary Computation method called Genetic Network Programming (GNP) is applied to generate programs such as Boolean functions. GNP is an extension of Genetic Algorithm (GA) and Genetic Programming (GP). It has a directed graph structure as gene and can search for solutions effectively. GNP has been mainly applied to dynamic problems and has shown better performances compared to GP. However, its application to static problems has not yet been studied well. Thus in this paper, GNP is applied to generate programs as its extension to solving static problems. In order to apply GNP to generating static problems, we introduced a new element, memory. In the proposed method, a GNP individual consists of a directed graph and a memory, while one in conventional GNP consists only of a directed graph. In the simulations, GNP succeeded in solving Even-n-Parity problem and Mirror Symmetry problem.
Cite this article as:S. Mabu, K. Hirasawa, Y. Matsuya, and J. Hu, “Genetic Network Programming for Automatic Program Generation,” J. Adv. Comput. Intell. Intell. Inform., Vol.9 No.4, pp. 430-436, 2005.Data files: