A method is presented to dynamically adapt the topology of a neural network using only the information of the learning set. The method, which simply consists of eliminating connections from an initial fully connected network, presents characteristics which can resemble some biological behavior. Several experimental results obtained with recurrent and multilayered networks are reported to demonstrate the capabilities of the proposed method.
Neural networks with self-adaptive topology / Marchesi, M; Orlandi, Gianni; Piazza, F; Uncini, Aurelio. - 5:(1991), pp. 2498-2501. [10.1109/ISCAS.1991.176034]
Neural networks with self-adaptive topology
ORLANDI, Gianni;UNCINI, Aurelio
1991
Abstract
A method is presented to dynamically adapt the topology of a neural network using only the information of the learning set. The method, which simply consists of eliminating connections from an initial fully connected network, presents characteristics which can resemble some biological behavior. Several experimental results obtained with recurrent and multilayered networks are reported to demonstrate the capabilities of the proposed method.File allegati a questo prodotto
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
