A generalization of the Cellular Neural Network paradigm is obtained by removing the uniformity constraint on weight values. Such Generalized CNNs are capable of new tasks, such as function approximation or associative memory. A stability analysis of these networks is presented. Adaptation and application of a gradient descent learning algorithm is then discussed.

Generalized CNN: potentials of a CNN with non-uniform weights / Balsi, Marco. - STAMPA. - (1992), pp. 129-134. (Intervento presentato al convegno Second IEEE International Workshop on Cellular Networks and their Applications tenutosi a Monaco, Germania).

Generalized CNN: potentials of a CNN with non-uniform weights

BALSI, Marco
1992

Abstract

A generalization of the Cellular Neural Network paradigm is obtained by removing the uniformity constraint on weight values. Such Generalized CNNs are capable of new tasks, such as function approximation or associative memory. A stability analysis of these networks is presented. Adaptation and application of a gradient descent learning algorithm is then discussed.
1992
Second IEEE International Workshop on Cellular Networks and their Applications
cellular neural networks; stability learning; associative processing; gradient methods
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Generalized CNN: potentials of a CNN with non-uniform weights / Balsi, Marco. - STAMPA. - (1992), pp. 129-134. (Intervento presentato al convegno Second IEEE International Workshop on Cellular Networks and their Applications tenutosi a Monaco, Germania).
File allegati a questo prodotto
File Dimensione Formato  
Balsi_Generalized-CNN_1992.pdf

accesso aperto

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Creative commons
Dimensione 346.15 kB
Formato Adobe PDF
346.15 kB Adobe PDF
Balsi_Generalized_1992.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 288.75 kB
Formato Adobe PDF
288.75 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/417590
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? ND
social impact