Predicting the generalization ability of neural networks resembling the nearest-neighbor algorithm (Contributo in atti di convegno)

Type

• Prodotto della ricerca (Classe)
• Contributo in atti di convegno (Classe)

Label

• Predicting the generalization ability of neural networks resembling the nearest-neighbor algorithm (Contributo in atti di convegno) (literal)

Anno

• 2000-01-01T00:00:00+01:00 (literal)

Alternative label

• M. Muselli (2000)
  Predicting the generalization ability of neural networks resembling the nearest-neighbor algorithm
  in Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN 2000), Como, Italy, 24-27 July 2000
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• M. Muselli (literal)

Pagina inizio

• 27 (literal)

Pagina fine

• 33 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

• IJCNN 2000: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroFascicolo

• I (literal)

Note

• ISI Web of Science (WOS) (literal)
• Scopu (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• M. Muselli: CNR-IEIIT, Genova, Italy (literal)

Titolo

• Predicting the generalization ability of neural networks resembling the nearest-neighbor algorithm (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume

• S. Amari, C.L. Giles, M. Gori, V. Piuri (literal)

Abstract

• The definition of nearest-neighbor probability p(C) is introduced to characterize classification problems with binary inputs. It measures the likelihood that two patterns, which are close according to the Hamming distance, are assigned to the same class. It is shown that the generalization ability gN,v(C) of neural networks that resemble the nearest- neighbor algorithm can be expressed as a function of p(C) and is upper bounded by p(C) when p(C) > 0.5. In the opposite case a proper operator, called complementation, is proposed to improve the classification process in the test phase. (literal)

Editore

• IEEE Computer Society (Editore)

Prodotto di

• Institute of Electronics, Computer and Telecommunication Engineering (IEIIT) (Istituto)

Autore CNR

• MARCO MUSELLI (Unità di personale interno)

Incoming links:

Prodotto

• Institute of Electronics, Computer and Telecommunication Engineering (IEIIT) (Istituto)
• http://www.cnr.it/ontology/cnr/individuo/modulo/ID2764

Autore CNR di

• MARCO MUSELLI (Unità di personale interno)

Editore di

• IEEE Computer Society (Editore)