A new learning algorithm is proposed for space-varying cellular neural networks, used to implement associative memories. The algorithm exhibits some peculiar features which make it very attractive: the finite precision of connection weights is automatically taken into account as a design constraint; no multiplication is needed for weight computation; learning can be implemented in fixed point digital hardware or simulated on a digital computer without numerical errors.

Perfetti, R., Costantini, G. (2001). Multiplierless digital learning algorithm for cellular neural networks. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I. FUNDAMENTAL THEORY AND APPLICATIONS, 48(5), 630-635 [10.1109/81.922467].

Multiplierless digital learning algorithm for cellular neural networks

COSTANTINI, GIOVANNI
2001-01-01

Abstract

A new learning algorithm is proposed for space-varying cellular neural networks, used to implement associative memories. The algorithm exhibits some peculiar features which make it very attractive: the finite precision of connection weights is automatically taken into account as a design constraint; no multiplication is needed for weight computation; learning can be implemented in fixed point digital hardware or simulated on a digital computer without numerical errors.
2001
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore ING-IND/31 - ELETTROTECNICA
English
Associative memories; Cellular neural networks; Learning
Perfetti, R., Costantini, G. (2001). Multiplierless digital learning algorithm for cellular neural networks. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I. FUNDAMENTAL THEORY AND APPLICATIONS, 48(5), 630-635 [10.1109/81.922467].
Perfetti, R; Costantini, G
Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
2001-Multiplierless Digital Learning Algorithm for CNN.pdf

accesso aperto

Licenza: Non specificato
Dimensione 230.78 kB
Formato Adobe PDF
230.78 kB Adobe PDF Visualizza/Apri

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/2108/52592
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact