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.| 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.
