Approximation properties of the neuro-fuzzy minimum function

The integration of fuzzy logic systems and neural networks in data driven nonlinear modeling applications has generally been limited to functions based upon the multiplicative fuzzy implication rule for theoretical and computational reasons. We derive a universal approximation result for the minimum fuzzy implication rule as well as a differentiable substitute function that allows fast optimization and function approximation with neuro-fuzzy networks.

MoreLess

Year of publication:	1999
Authors:	Gottschling, Andreas ; Kreuter, Christof
Publisher:	Frankfurt a. M. : Deutsche Bank Research
Subject:	Nichtlineare Optimierung \| Neuronale Netze \| Theorie \| Fuzzy Logic \| Neural Networks \| Nonlinear Modeling \| Optimization

More details

Series:	Research Notes ; 99-3
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	821922408 [GVK] hdl:10419/40292 [Handle] RePEc:zbw:dbrrns:993 [RePEc]
Classification:	C0 - Mathematical and Quantitative Methods. General ; C2 - Econometric Methods: Single Equation Models ; C4 - Econometric and Statistical Methods: Special Topics ; C6 - Mathematical Methods and Programming
Source:	EconStor

Persistent link: https://ebvufind01.dmz1.zbw.eu/10010301773