Efficient constructive techniques for training Switching Neural Networks (Contributo in volume (capitolo o saggio))

Type
Label
  • Efficient constructive techniques for training Switching Neural Networks (Contributo in volume (capitolo o saggio)) (literal)
Anno
  • 2009-01-01T00:00:00+01:00 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi
  • 10.1007/978-3-642-04512-7_2 (literal)
Alternative label
  • E. Ferrari, M. Muselli (2009)
    Efficient constructive techniques for training Switching Neural Networks
    Springer-Verlag, Berlin (Germania) in Constructive Neural Networks, 2009
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • E. Ferrari, M. Muselli (literal)
Pagina inizio
  • 25 (literal)
Pagina fine
  • 48 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#citta
  • Berlin (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume
  • Constructive Neural Networks (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana
  • 258 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note
  • Volume: 258, Pagine: 25-48 Collana: Studies in Computational Intelligence (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatori
  • L. Franco, D.A. Elizondo, J.M. Jerez (literal)
Note
  • ISI Web of Science (WOS) (literal)
  • Scopu (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • E. Ferrari, M. Muselli: CNR-IEIIT, Italy (literal)
Titolo
  • Efficient constructive techniques for training Switching Neural Networks (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#inCollana
  • Constructive Neural Networks (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn
  • 978-3-642-04511-0 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume
  • L. Franco, D.A. Elizondo, J.M. Jerez (literal)
Abstract
  • A general constructive approach for training neural networks in classification problems is presented. This approach is used to construct a particular connectionist model, named Switching Neural Network (SNN), based on the conversion of the original problem in a Boolean lattice domain. The training of an SNN can be performed through a constructive algorithm, called Switch Programming (SP), based on the solution of a proper linear programming problem. Since the execution of SP may require an excessive computational time, an approximate version of it, named Approximate Switch Programming (ASP) has been developed. Simulation results obtained on the StatLog benchmark show the good quality of the SNNs trained with SP and ASP. (literal)
Editore
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Prodotto
Autore CNR di
Editore di
Insieme di parole chiave di
data.CNR.it