Intelligent Hybrid Systems pp 59-89 | Cite as

# Novel Neural Algorithms for Solving Fuzzy Relation Equations

## Abstract

Due to the difficulty in a given system of using neural networks to solve fuzzy relation equations, the best learning rate sometimes cannot be decided easily and strict theoretical analyses on convergence of algorithms are not given. To overcome these problems, we present in this chapter some novel neural algorithms based on fuzzy δ rules. We first describe such algorithms for max-min operator networks, then we demonstrate that these algorithms can also be extended to max-times operator network. Important results include some improved fuzzy δ rules, a convergence theorem, and an equivalence theorem which reflects that fuzzy theory and neural networks can reach the same goal by different routes. We also discuss the fuzzy bidirectional associative memory network and its training algorithms, and prove all important theorems with additional simulation and comparison results.

Furthermore, we propose a more powerful algorithm for solving many types of fuzzy relation equations. The algorithm is based on a specially designed fuzzy neuron. This fuzzy neuron is found by replacing the operators of the traditional neuron by a pair of abstract fuzzy operators such as
\(\left( {\hat{ + },\hat{ \bullet }} \right)\), which we call fuzzy neuron operators. Afterwards, we discuss the relationship between the fuzzy neuron operators and the *t*-norm and *t*-conorm, and point out that fuzzy neuron operators are based on the *t*-norm, but are much wider than the *t*-norm. And finally, we report some simulation results of some pairs of typical compositional operators.

## Keywords

Fuzzy System Stable Point Fuzzy Neural Network Maximum Solution Fuzzy Relation Equation## Preview

Unable to display preview. Download preview PDF.

## References

- [1]A. Blanco, M. Delgado, and I. Requena, “Identification of fuzzy relational equations by fuzzy neural networks,”
*Fuzzy Sets and Systems*71 (1995), 215–226.CrossRefGoogle Scholar - [2]J. J. Buckley and Y. Hayashi, “Fuzzy neural networks: A survey,”
*Fuzzy Sets and Systems*66 (1994), 1–13.MathSciNetCrossRefGoogle Scholar - [3]A. Di Nola, W. Pedrycz, S. Sessa, and P. Z. Wang, “Fuzzy relation equations under a class of triangular norms: a survey and new results,”
*Stochastica*8 (1984), 89–145.Google Scholar - [4]A. Di Nola, W. Pedrycz, and S. Sessa, “Some theoretical aspects of fuzzy relation equations describing fuzzy systems,”
*Inform. Sci.*34 (1984), 241–264.MathSciNetzbMATHCrossRefGoogle Scholar - [5]S. Gottwald, “Approximately solving fuzzy relation equations: Some mathematical results and some heuristic proposals,”
*Fuzzy Sets and Systems*66 (1994), 175–193.MathSciNetzbMATHCrossRefGoogle Scholar - [6]M. M. Gupta and D. H. Rao, “On the principles of fuzzy neural networks,”
*Fuzzy Sets and Systems*61 (1994), 1–18.MathSciNetCrossRefGoogle Scholar - [7]G. J. Klir and B. Yuan,
*Fuzzy Sets and Fuzzy Logic, Theory and Applications*(Prentice Hall PTR, 1995).Google Scholar - [8]B. Kosko,
*Neural Networks and Fuzzy Systems*(Prentice Hall, 1990).Google Scholar - [9]X. Li,
*Researches on a self-learning and adaptive fuzzy systems and fuzzy neural network*, PhD thesis, Beijing University of Post and Telecommunications, Beijing, 1994.Google Scholar - [10]X. Li, P. Z. Wang, and C. Luo,
*Fuzzy Neural Network*, Guizhou Science and Technology Press, 1994 (in Chinese).Google Scholar - [11]X. Li and Sh. Bai, “A neural algorithm to solve some fuzzy relation equations,” Proc. Int. Conf. on Neural Information Processing, 417–420, Beijing 1995.Google Scholar
- [12]X. Li, “A fuzzy perceptron and its convergence theorem,” Proc. Fourth Int. Conf. for Young Computer Scientists, 506–512, Beijing, 1995.Google Scholar
- [13]X. Li and D. Ruan, “Novel neural algorithms based on fuzzy
*δ*rules for solving fuzzy relation equations: Part I,” accepted by*Fuzzy Sets and Systems*, 1996.Google Scholar - [14]X. Li and D. Ruan, “Novel neural algorithms based on fuzzy
*δ*rules for solving fuzzy relation equations: Part II”, accepted by*Fuzzy Sets and Systems*, 1997.Google Scholar - [15]C. Luo, An
*Introduction to Fuzzy Sets*, Beijing Normal University Press, 1989 (in Chinese).Google Scholar - [16]M. Miyakoshi and M Shimobo, “Solutions of fuzzy relational equations with triangular norms,”
*Fuzzy Sets and Systems*16 (1985), 53–63.MathSciNetzbMATHCrossRefGoogle Scholar - [17]W. Pedrycz, “Relational Structures in fuzzy sets and neurocomputation,” Proc. Int. Conf. on Fuzzy Logic and Neural Networks, lizuka (1990), 235–238.Google Scholar
- [18]E. Sanchez, “Resolution of composite fuzzy relation equations,”
*Inform. and Control*30 (1976), 38–48.zbMATHCrossRefGoogle Scholar - [19]S. Sessa, “Some results in the setting of fuzzy relation equation theory,”
*Fuzzy Sets and Systems*14 (1984), 237–248.MathSciNetCrossRefGoogle Scholar