Consiglio Nazionale delle Ricerche

Tipo di prodottoContributo in atti di convegno
TitoloA Hybrid Adaptive-Resonance-Theory/Error-Back-Propagation (ART/EBP) architecture for supervised learning
Anno di pubblicazione1991
Formato
  • Elettronico
  • Cartaceo
Autore/iS. Brofferio, V. Rampa, F. Soldovieri, F. Stehle
Affiliazioni autoriDipartimento di Elettronica, Politecnico di Milano, P.za L. da Vinci 32, 20133 Milano; CSTS-CNR, c/o Dipartimento di Elettronica, P.za L. da Vinci 32, 20133 Milano
Autori CNR e affiliazioni
  • VITTORIO RAMPA
Lingua/e
  • inglese
AbstractOne of the most interesting engineering applications of neural networks is the design of recognition architectures for classifing pattern vectors. The architectures are characterized by their topology and, if the pattern vector space partitioning is not predetermined, by the learning algorithm. The complexity of a neural architecture depends on the partitioning of the pattern vector space into class regions and on the learning algorithm. However the hypothesis of stationary probabilistic characteristics of the input vector and of the classification correspondence is sometimes over-simplifying. Moreover each learning algorithm has its specific advantages and limitations so that it is useful to investigate hybrid architectures that take the advantages of the specific algorithms while avoiding their limitations. As we are interested in limiting the architecture complexity, we investigate algorithms with a low number of nodes and/or interconnections, with the additional benefit of a reduced cost of the learning phase. Architectures based on the Adaptive-Resonance-Theory (ART) are based on unsupervised learning and avoid the stability/plasticity problem, that is they allow the number of recognition nodes to be augmented when the probabilistic characteristics change. No loss of the previous recognition capabilities occurs so that the learning and recognition phases are purposely intermingled.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da131
Pagine a138
Pagine totali8
Rivista-
Numero volume della rivista-
Serie/Collana-
Titolo del volumeProceedings of 4th Italian Workshop on Parallel Architectures and Neural Networks 1991
Numero volume della serie/collana-
Curatore/i del volumeE. R. Caianiello
ISBN981-02-0763-8
DOI-
Editore
  • World Scientific, Singapore (Singapore)
Verificato da refereeSì: Nazionale
Stato della pubblicazione-
Indicizzazione (in banche dati controllate)
  • ISI Web of Science (WOS) (Codice:A1991BV14Z00016)
Parole chiave-
Link (URL, URI)-
Titolo convegno/congresso4th Italian Workshop on Parallel Architectures and Neural Networks 1991
Luogo convegno/congressoVietri
Data/e convegno/congressoMay 1991
RilevanzaNazionale
RelazioneContributo
Titolo parallelo-
Note/Altre informazioniIDS Number: BV14Z
Strutture CNR
  • IEIIT — Istituto di elettronica e di ingegneria dell'informazione e delle telecomunicazioni
Moduli CNR
    Progetti Europei-
    Allegati
    • A Hybrid Adaptive-Resonance-Theory/Error-Back-Propagation (ART/EBP) architecture for supervised learning
      Descrizione: Published paper