Multi-Layered GMDH-Type Neural Network Self-Sеlecting Optimum Neural Network Architecture and Its Application to Nonlinear System Identification. Tadashi Kondo, Junji Ueno. IWIM, Prague, 2007.
Article (in pdf)
Abstract. In this study, a new multi-layered Group Method of Data Handling (GMDH)-type neural network self-selecting optimum neural network architecture is proposed. We call this algorithm as revised GMDH-type neural network algorithm self-selecting optimum neural network architecture. Revised GMDH-type neural network algorithm has an ability of self-selecting optimum neural network architecture from three neural network architectures such as sigmoid function neural network, radial basis function (RBF) neural network and polynomial neural network. Revised GMDH-type neural network also has abilities of self-selecting the number of layers, the number of neurons in hidden layers and useful input variables. This algorithm is applied to the nonlinear system identification problem and it is shown that this algorithm is useful for the nonlinear system identification because optimum neural network architecture is automatically organized.
Keywords. GMDH, Neural network, System identification
References.
- Kondo T.: GMDH neural network algorithm using the heuristic self-organization method and its application to the pattern identification problem, Proc. of the 37th SICE Annual Conference, p.1143-1148,1998.
- Kondo T.: Revised GMDH-type neural networks using prediction error criterions AIC and PSS, Proc. of SCIS & ISIS 2004, WP-6-4, p.1-6, 2004.
- Kondo T., Pandya A.S: Identification of the multi-layered neural networks by revised GMDH-type neural network algorithm with PSS criterion, Knowledge based intelligent information and engineering systems, p.1051-1059, 2004.
- Farlow S.J.ed.: Self-organizing methods in modeling, GMDH-type algorithm, Marcel Dekker, Inc., New York, 1984.
- Ivakhnenko A.G.: Heuristic self-organization in problems of engineering cybernetics, Automatica, Vo.6, No.2, p.207-219, 1970.
- Tamura H., Kondo T.: Heuristics free group method of data handling algorithm of generating optimum partial polynomials with application to air pollution prediction, Int. J. System Sci., Vol.11, No.9, p.1095-1111, 1980.
- Draper N.R., Smith H.: Applied Regression Analysis, John Wiley and Sons, New York, 1981.
