Hybrid Inductive Models: Topology of Model can Reveal much about Problem. Pavel Naplava, Pavel Kordik. IWIM, Prague, 2007.

 Article (in pdf)

Abstract. In this paper we study how much information about a problem we can get from topology of inductive models build to model this problem. Our experiments show that for each problem, combination of various units is the most efficient. Also the performance of optimization methods varies on different problems. When we study the topology of models, we can extract much information about problems modeled.

Keywords. Inductive modeling, hybrid models.

References.

1. Ivakhnenko A. G.: Polynomial theory of complex systems. IEEE Transactions on Systems, Man, and Cybernetics, SMC-1(1):364378, 1971.

2. P. Kordik. Fully Automated Knowledge Extraction using Group of Adaptive Models Evolution. PhD thesis, Dep. of Comp. Sci. and Computers, FEE, CTU Prague, Czech Republic, September 2006.

3. Mahfoud, S.W. (1995),'Niching Methods for Genetic Algorithms'(95001), Technical report, Illinois Genetic Algorithms Laboratory (IlliGaL), University of Ilinios at Urbana-Champaign.