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.
|Titolo:||Discrete-time cellular neural networks for associative memories: a new design method via iterative learning and forgetting algorithms|
|Data di pubblicazione:||1996|
|Nome del convegno:||38th Midwest Symposium on Circuits and Systems, MWSCAS'95|
|Digital Object Identifier (DOI):||10.1109/MWSCAS.1995.504496|
|Appare nelle tipologie:||4.1 Contributo in Atti di convegno|