EconStor >
Deutsche Bank Research, Frankfurt am Main >
Research Notes, Deutsche Bank Research >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/40292
  
Title:Approximation properties of the neuro-fuzzy minimum function PDF Logo
Authors:Gottschling, Andreas
Kreuter, Christof
Issue Date:1999
Series/Report no.:Research notes in economics & statistics 99-3
Abstract: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.
Subjects:Fuzzy Logic
Neural Networks
Nonlinear Modeling
Optimization
JEL:C0
C2
C4
C6
Document Type:Working Paper
Appears in Collections:Research Notes, Deutsche Bank Research

Files in This Item:
File Description SizeFormat
303948884.pdf978.98 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/40292

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.