Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloIs pocket algorithm optimal?
Anno di pubblicazione1995
FormatoCartaceo
Autore/iM. Muselli
Affiliazioni autoriM. Muselli: CNR-IEIIT, Genova, Italy
Autori CNR e affiliazioni
  • MARCO MUSELLI
Lingua/e
  • inglese
AbstractMost learning algorithms for single neuron are not able to provide for any classification problem the weight vector which satisfies the maximum number of input-output relations contained in the training set. An important exception is given by the pocket algorithm: it repeatedly executes the perceptron algorithm and maintains (in the pocket) the weight vector which is remained unchanged for the highest number of iterations. A proper convergence theorem ensures the achievement of an optimal configuration with probability one when the number of iterations grows indefinitely. This theoretical result is used for showing the good convergence properties of other learning methods for multilayered neural networks, which employ pocket algorithm as a basic task. In the present paper a new formulation of the pocket convergence theorem is given; a rigorous proof corrects some formal and substantial errors which invalidate previous theoretical results. In particular it is shown that the optimality of the asymptotical solution is ensured only if the number of permanences for the pocket vector lies in a proper interval of the real axis which bounds depend on the number of iterations.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da287
Pagine a297
Pagine totali-
RivistaLecture notes in computer science
Attiva dal 1973
Editore: Springer - Berlin
Paese di pubblicazione: Germania
Lingua: multilingue
ISSN: 0302-9743
Titolo chiave: Lecture notes in computer science
Titolo proprio: Lecture notes in computer science.
Titolo abbreviato: Lect. notes comput. sci.
Titoli alternativi:
  • Lecture notes in computer science. Lecture notes in artificial intelligence
  • Lecture notes in artificial intelligence
  • LNCS. Lecture notes in computer science (Print)
  • Lecture notes in computer science (Print)
  • Lecture notes in computer science. LNAI. Lecture notes in artificial intelligence
  • Lecture notes in computer science. Lecture notes in bioinformatics (Print)
  • Lecture notes in computer science. Journal subline
Numero volume della rivista904
Fascicolo della rivista-
DOI10.1007/3-540-59119-2_185
Verificato da refereeSì: Internazionale
Stato della pubblicazione-
Indicizzazione (in banche dati controllate)-
Parole chiave-
Link (URL, URI)-
Titolo parallelo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IEIIT — Istituto di elettronica e di ingegneria dell'informazione e delle telecomunicazioni
Moduli CNR
    Progetti Europei-
    Allegati
    • Is pocket algorithm optimal?