A neural net topology for bidirectional fuzzy-neuro transformation
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 1511-1518
- https://doi.org/10.1109/fuzzy.1995.409879
Abstract
In this paper, we propose an integrated neuro-fuzzy system (INFS) that facilitates the functional equivalent conversion between fuzzy systems and neural networks thus combining the advantages of both paradigms. The basis for the INFS constitutes a special neural network architecture with a structure corresponding to that of a fuzzy model. In a repeated cycle, knowledge acquired from an expert is converted from a fuzzy system to a neural net which is applied to a target system to learn from the data. After completed adaptation the neural network is translated back into a fuzzy model. First results demonstrate the significant performance with respect to data-driven optimization of fuzzy system components.Keywords
This publication has 9 references indexed in Scilit:
- On the principles of fuzzy neural networksFuzzy Sets and Systems, 1994
- An Introduction to Fuzzy ControlPublished by Springer Nature ,1993
- Self-learning fuzzy controllers based on temporal backpropagationIEEE Transactions on Neural Networks, 1992
- Fuzzy basis functions, universal approximation, and orthogonal least-squares learningIEEE Transactions on Neural Networks, 1992
- Learning and tuning fuzzy logic controllers through reinforcementsIEEE Transactions on Neural Networks, 1992
- Fuzzy Model Identification and Self-Learning for Dynamic SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1987
- Identification in fuzzy systemsIEEE Transactions on Systems, Man, and Cybernetics, 1984
- The evaluation of fuzzy models derived from experimental dataFuzzy Sets and Systems, 1980
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943