Artificial Neural Networks are Zero-Order TSK Fuzzy Systems

Authors:
C. J. Mantas;J. M. Puche
Affiliations:
Dept. of Comput. Sci. & Artificial Intell., Univ. of Granada, Granada;-
Venue:
IEEE Transactions on Fuzzy Systems
Year:
2008

Citing 0
Cited 6

An ANFIS Based Fuzzy Synthesis Judgment for Transformer Fault Diagnosis

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
A fuzzy neural network with fuzzy impact grades

Neurocomputing
On the equivalence of single input type fuzzy inference methods

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
A probabilistic fuzzy approach to modeling nonlinear systems

Neurocomputing
A species-based improved electromagnetism-like mechanism algorithm for TSK-type interval-valued neural fuzzy system optimization

Fuzzy Sets and Systems
Fuzzy Radial Basis Function Neural Networks with information granulation and its parallel genetic optimization

Fuzzy Sets and Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, the functional equivalence between the action of a multilayered feed-forward artificial neural network (NN) and the performance of a system based on zero-order TSK fuzzy rules is proven. The resulting zero-order TSK fuzzy systems have the two following features: (A) the product t-norm is used to add IF-part fuzzy propositions of the obtained rules and (B) their inputs are the same as the initial neural networkNN ones. This fact makes us gain an understanding of the ANN-embedded knowledge. Besides, it allows us to simplify the architecture of a network through the reduction of fuzzy propositions in its equivalent zero-order TSK system. These advantages are the result of applying fuzzy system area properties on the neural networkNN area. They are illustrated with several examples.