The defuzzification of a type-2 fuzzy set is a two-stage process consisting of firstly type-reduction, and a secondly defuzzification of the resultant type-1 set. All accurate type reduction methods used to build fuzzy classifiers are based on the recursive Karnik-Mendel algorithm, which is troublesome to obtain a feedforward type-2 fuzzy network structure. Moreover, the KM algorithm and its modifications complicate the learning process due to the non-differentiability of the maximum and minimum functions. Therefore, this paper proposes to use the smooth maximum function to develop a new structure of the fuzzy type-2 classifier.
Type-2 Fuzzy Classifier with Smooth Type-Reduction / Nieszporek, K; De Magistris, G; Napoli, C; Starczewski, Jt. - 13588:(2023), pp. 193-202. (Intervento presentato al convegno Artificial Intelligence and Soft Computing tenutosi a Zakopane; Poland) [10.1007/978-3-031-23492-7_17].
Type-2 Fuzzy Classifier with Smooth Type-Reduction
De Magistris, GSecondo
Formal Analysis
;Napoli, CPenultimo
Supervision
;
2023
Abstract
The defuzzification of a type-2 fuzzy set is a two-stage process consisting of firstly type-reduction, and a secondly defuzzification of the resultant type-1 set. All accurate type reduction methods used to build fuzzy classifiers are based on the recursive Karnik-Mendel algorithm, which is troublesome to obtain a feedforward type-2 fuzzy network structure. Moreover, the KM algorithm and its modifications complicate the learning process due to the non-differentiability of the maximum and minimum functions. Therefore, this paper proposes to use the smooth maximum function to develop a new structure of the fuzzy type-2 classifier.File | Dimensione | Formato | |
---|---|---|---|
Nieszporek_Preprint_Type-2_2022.pdf
accesso aperto
Note: DOI10.1007/978-3-031-23492-7_17
Tipologia:
Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza:
Creative commons
Dimensione
441.28 kB
Formato
Adobe PDF
|
441.28 kB | Adobe PDF | |
Nieszporek_Type-2_2023.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.37 MB
Formato
Adobe PDF
|
2.37 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.