Please use this identifier to cite or link to this item:
https://hdl.handle.net/10419/40292
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Gottschling, Andreas | en |
dc.contributor.author | Kreuter, Christof | en |
dc.date.accessioned | 2010-07-27 | - |
dc.date.accessioned | 2010-09-24T14:30:10Z | - |
dc.date.available | 2010-09-24T14:30:10Z | - |
dc.date.issued | 1999 | - |
dc.identifier.uri | http://hdl.handle.net/10419/40292 | - |
dc.description.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. | en |
dc.language.iso | eng | en |
dc.publisher | |aDeutsche Bank Research |cFrankfurt a. M. | en |
dc.relation.ispartofseries | |aResearch Notes |x99-3 | en |
dc.subject.jel | C0 | en |
dc.subject.jel | C2 | en |
dc.subject.jel | C4 | en |
dc.subject.jel | C6 | en |
dc.subject.ddc | 330 | en |
dc.subject.keyword | Fuzzy Logic | en |
dc.subject.keyword | Neural Networks | en |
dc.subject.keyword | Nonlinear Modeling | en |
dc.subject.keyword | Optimization | en |
dc.subject.stw | Nichtlineare Optimierung | en |
dc.subject.stw | Neuronale Netze | en |
dc.subject.stw | Theorie | en |
dc.title | Approximation properties of the neuro-fuzzy minimum function | - |
dc.type | Working Paper | en |
dc.identifier.ppn | 821922408 | en |
dc.rights | http://www.econstor.eu/dspace/Nutzungsbedingungen | en |
dc.identifier.repec | RePEc:zbw:dbrrns:993 | en |
Files in This Item:
Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.