Structure and parameter learning of neuro-fuzzy systems: A methodology and a comparative study

Article type: Research Article

Authors: Paiva, Rui Pedro | Dourado, António

Affiliations: CISUC -- Centro de Informática e Sistemas da Universidade de Coimbra, Department of Informatics Engineering, Pólo II of the University of Coimbra, P 3030 Coimbra, Portugal

Note: [] Correspondent author. E-mail: [email protected]; URL: http://www.dei.uc.pt/~dourado

Abstract: A methodology and experimental comparison of neuro-fuzzy structures, namely linguistic and zero and first-order Takagi-Sugeno, are developed. The implementation of the model is conducted through the training of a neuro-fuzzy network, i.e., a neural net architecture capable of representing a fuzzy system. In the first phase, the structure of the model is obtained by subtractive clustering, which allows the extraction of a set of relevant rules based on a set of representative input-output data samples. Membership functions with two-sided Gaussian functions are proposed and discussed. In the second phase, the model parameters are tuned via the training of a neural network. Furthermore, different fuzzy operators are compared, as well as regular and two-sided Gaussian functions.

Keywords: neuro-fuzzy systems, structure learning, parameter learning, clustering

Journal: Journal of Intelligent & Fuzzy Systems, vol. 11, no. 3-4, pp. 147-161, 2001