In this paper a synthesis procedure of discrete-time Cellular Neural Networks (DTCNN's) for associative memories with iterative learning and forgetting algorithms is developed, by which each pattern to be stored is learnt one at a time and each pattern to be forgotten is deleted one at a time. The proposed approach exploits the properties of pseudo inverse matrices and preserves the local connection feature of DTCNN's.
Discrete-time cellular neural networks for associative memories: a new design method via iterative learning and forgetting algorithms / Brucoli, M.; Carnimeo, L.; Grassi, G.. - STAMPA. - (1996), pp. 542-545. (Intervento presentato al convegno 38th Midwest Symposium on Circuits and Systems, MWSCAS'95 tenutosi a Rio de Janeiro, Brazil nel August 13-16, 1995) [10.1109/MWSCAS.1995.504496].
Discrete-time cellular neural networks for associative memories: a new design method via iterative learning and forgetting algorithms
M. Brucoli;L. Carnimeo;
1996-01-01
Abstract
In this paper a synthesis procedure of discrete-time Cellular Neural Networks (DTCNN's) for associative memories with iterative learning and forgetting algorithms is developed, by which each pattern to be stored is learnt one at a time and each pattern to be forgotten is deleted one at a time. The proposed approach exploits the properties of pseudo inverse matrices and preserves the local connection feature of DTCNN's.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
