Abstract
The two topics of this chapter are how to design and train a neural net to: (1) approximate a solution to a fuzzy equation; and (2) approximate certain fuzzy functions. All the neural nets in this chapter will share the same design constraints of some weights must be positive and the rest negative. Figure 6.1 shows the sign constraints on the weights of a simple 1 - 3 - 1 neural net. The computation of y, from given input x, is the same as discussed in Chapter 3. There are no sign constraints on the shift terms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References Chapter 6
J.J. Buckley and E. Eslami: Solving Fuzzy Equations Using Neural Nets, Proc. First Annual Computer Conference of the Computer Soc. of Iran, Teheran, Iran, Dec. 25–28, 1995, pp. 237–245.
J.J. Buckley and E. Eslami: Neural Net Solutions to Fuzzy Problems: The Quadratic Equation, Fuzzy Sets and Systems 86 (1997) pp. 289–298.
J.J. Buckley and Y. Hayashi: Solving Fuzzy Equations Using Neural Nets, Proc. NAFIPS/ISUMA, Univ. Maryland, Sept., 1995, pp. 302–304.
J.J. Buckley and Y. Hayashi.: Neural Net Solutions to Fuzzy Linear Programming, Proc. FUZZ-IEEE ’96, New Orleans, Sept. 8–11, 1996, Vol. 3, pp. 15631566.
J.J. Buckley and Y. Hayashi: Neural Net Approximations to Solutions of Systems of Fuzzy Linear Equations, Proc. ICNN-IEEE ’97, Houston, Texas, June 9–13, 1997, pp. 2355–2358.
J.J. Buckley and Y. Hayashi: Neural Nets Can Be Universal Approximators for Fuzzy Functions, Proc. ICNN-IEEE ’97, Houston, Texas, June 9–13, 1997, pp. 2347–2350.
J.J. Buckley and Y. Hayashi: Can Neural Nets Be Universal Approximators for Fuzzy Functions? Proc. FUZZ-IEEE ‘87, Barcelona, Spain, July 1–5, 1997, Vol. 2, pp. 1101–1104.
J.J. Buckley and Y. Hayashi: Can Neural Nets be Universal Approximators for Fuzzy Functions? Fuzzy Sets and Systems, to appear.
J.J. Buckley and Y. Qu: Solving Fuzzy Equations: A New Solution Concept, Fuzzy Sets and Systems 39 (1991) pp. 291–301.
J.J. Buckley and Y. Qu: Solving Fuzzy Equations, Fuzzy Sets and Systems 50 (1992) pp. 1–14.
J.J. Buckley, E. Eslami and Y. Hayashi: Solving Fuzzy Equations Using Neural Nets, Fuzzy Sets and Systems 86 (1997) pp. 271–278.
J.J. Buckley, T. Feuring and Y. Hayashi: Neural Net Solutions to Systems of Fuzzy Linear Equations, in: B. M. Ayyub and M. M. Gupta (eds.), Uncertainty Analysis in Engineering and the Sciences, Kluwer Academic Publishers, pp. 213–232, 1998.
J.J. Buckley, T. Feuring and Y. Hayashi: Neural Net Solution to Fuzzy Linear Programming, Fuzzy Sets and Systems, to appear.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Buckley, J.J., Feuring, T. (1998). Neural Nets Solve Fuzzy Problems. In: Fuzzy and Neural: Interactions and Applications. Studies in Fuzziness and Soft Computing, vol 25. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1881-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1881-9_6
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-662-11807-8
Online ISBN: 978-3-7908-1881-9
eBook Packages: Springer Book Archive