Functional equivalence between S-neural networks and fuzzy models

Authors:
Claudio Moraga;Karl-Heinz Temme
Affiliations:
Department of Computer Science, Computer Engineering and Computing Education. University of Dortmund/ 44221 Dortmund/ Germany;Department of Computer Science, Computer Engineering and Computing Education. University of Dortmund/ 44221 Dortmund/ Germany
Venue:
Technologies for constructing intelligent systems
Year:
2002

Citing 8
Cited 0

Multilayer feedforward networks are universal approximators

Neural Networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
NN-driven fuzzy reasoning

International Journal of Approximate Reasoning
Neural network implementation of fuzzy logic

Fuzzy Sets and Systems
Parallel distributed processing in the complex domain

Parallel distributed processing in the complex domain
Fuzzy Systems as Universal Approximators

IEEE Transactions on Computers
Application of Neuro-Fuzzy Networks to the Identification and Control of Nonlinear Dynamical Systems

IPMU '92 Proceedings of the 4th International Conference on Processing and Management of Uncertainty in Knowledge-Based Systems: Advanced Methods in Artificial Intelligence
Are artificial neural networks black boxes?

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A family of S-functions is introduced and characterized. S-functions may be used as activation functions in neural networks and allow the interpretation of the activity of the artificial neurons as fuzzy if-then rules, where the degree of satisfaction of the premises for a given input is calculated by means of the symmetric summation. These rules are appropriate to model compensating systems.