DocumentCode :
293488
Title :
A neural net topology for bidirectional fuzzy-neuro transformation
Author :
Hauptmann, Werner ; Heesche, Kai
Author_Institution :
Corp. Res. & Dev., Siemens AG, Munich, Germany
Volume :
3
fYear :
1995
fDate :
20-24 Mar 1995
Firstpage :
1511
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 :
fuzzy neural nets; neural net architecture; INFS; bidirectional fuzzy-neuro transformation; data-driven optimization; functional equivalent conversion; integrated neuro-fuzzy system; neural net topology; neural network architecture; repeated cycle; Feedforward neural networks; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Network topology; Neural networks; Power system modeling; Research and development; System testing; Tin;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int
Conference_Location :
Yokohama
Print_ISBN :
0-7803-2461-7
Type :
conf
DOI :
10.1109/FUZZY.1995.409879
Filename :
409879
Link To Document :
بازگشت