Abstract
The presented algorithm of fuzzy back propagation used in the teaching phase of a neural fuzzy controller combines the best features of two selected soft computing elements: fuzzy logic and the selected structure of artificial neural network. This approach is the expansion of the classical algorithm of back propagation by use of not only binary, but also any values from the range [0…1] in the teaching sequences and the selection of the value of the teaching factor η using the theory of fuzzy sets.
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
Cybenko G.: Approximation by Superpositions of a Sigmoidal Function. Mathematics of Control, Signals and Systems 2 (1989) 303–314
Figueiredo M, Gomide F.: Design of Fuzzy Systems Using Neurofuzzy Networks. IEEE Transactions on Fuzzy Systems 7 (1999) 815–828
Oh S.H., Lee S.Y.: A new Error function at Hidden Layers for Fast Training of Multilayer perceptrons IEEE Transactions on Neural Networks 7 (1999) 960–964
Psaltis D., Sideris A., Yamamura A.: A multilayered neural network controller. IEEE Control System Magazin 4 (1988) 44–48
Rumelhart D., Hinton G., Williams R.: Learning representations by backpropagating errors. Nature 323 (1986) 533–536
Simpson P.: Artificial neural systems. Pergamon Pres, USA (1990)
Song Q, Xiao J., Soh Y.C.: Robust Bacpropagation Training Algorithm for Multilayered Neural Tracking Controller. IEEE Transactions on Fuzzy Systems 8 (1999) 1133–1141
Werbos P.: Neurocontrol and fuzzy logic: connections and designs. Inter. j. of Approximation Reasoning 6 (1992) 185–219
Zadeh L. A.: Fuzzy sets. Information and Control 8 (1965) 338–353
Zimmermann H.: Fuzzy Sets Theory and its Applications. Kluwer, Boston, 2nd edition, (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bedzak, M. (2001). Fuzzy-η for Back Propagation Networks. In: Reusch, B. (eds) Computational Intelligence. Theory and Applications. Fuzzy Days 2001. Lecture Notes in Computer Science, vol 2206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45493-4_13
Download citation
DOI: https://doi.org/10.1007/3-540-45493-4_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42732-2
Online ISBN: 978-3-540-45493-9
eBook Packages: Springer Book Archive