Fuzzy neural networks with fuzzy weights and fuzzy biases
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1650-1655 vol.3
- https://doi.org/10.1109/icnn.1993.298804
Abstract
An architecture of multi-layer feedforward neural networks whose weights and biases are given as fuzzy numbers is proposed. The fuzzy neural network with the proposed architecture maps an input vector of real numbers to a fuzzy output. The input-output relation of each unit is defined by the extension principle. A learning algorithm of the fuzzy neural networks is derived for real input vectors and fuzzy target outputs. The derived learning algorithm is extended to the case of fuzzy input vectors and fuzzy target outputs.Keywords
This publication has 7 references indexed in Scilit:
- The concept of a linguistic variable and its application to approximate reasoning—IIPublished by Elsevier ,2003
- An architecture of neural networks for input vectors of fuzzy numbersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Neural networks that learn from fuzzy if-then rulesIEEE Transactions on Fuzzy Systems, 1993
- Fuzzy regression analysis using neural networksFuzzy Sets and Systems, 1992
- Regression analysis with interval model by neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- Linear Regression Analysis with Fuzzy ModelIEEE Transactions on Systems, Man, and Cybernetics, 1982