In a discrete of a neural network, from a limitation on the rank of the matrix of ``coupling coefficients'', an upper bound for the maximum length of the transients is derived, generalizing the analogue result of Caianello (1966a) for the case of rank one. A counterexample shows that the limitation found is the best possible involving only the rank of the matrix.
Accardi, L. (1971). Rank and reverberations in neural networks, 8(5), 163-164.
Rank and reverberations in neural networks
ACCARDI, LUIGI
1971-01-01
Abstract
In a discrete of a neural network, from a limitation on the rank of the matrix of ``coupling coefficients'', an upper bound for the maximum length of the transients is derived, generalizing the analogue result of Caianello (1966a) for the case of rank one. A counterexample shows that the limitation found is the best possible involving only the rank of the matrix.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
Ac71.pdf
accesso aperto
Dimensione
173.96 kB
Formato
Adobe PDF
|
173.96 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.