In the context of attractor neural networks, we study how the equilibrium analog neural activities, reached by the network dynamics during memory retrieval, may improve storage performance by reducing the interferences between the recalled pattern and the other stored ones. We determine a simple dynamics that stabilizes network states which are highly correlated with the retrieved pattern, for a number of stored memories that does not exceed alpha*N, where alpha* is-an-element-of [0,0.41] depends on the global activity level in the network and N is the number of neurons.
Response functions improving performance in analog attractor neural networks
Brunel, Nicolas;Zecchina, Riccardo
1994
Abstract
In the context of attractor neural networks, we study how the equilibrium analog neural activities, reached by the network dynamics during memory retrieval, may improve storage performance by reducing the interferences between the recalled pattern and the other stored ones. We determine a simple dynamics that stabilizes network states which are highly correlated with the retrieved pattern, for a number of stored memories that does not exceed alpha*N, where alpha* is-an-element-of [0,0.41] depends on the global activity level in the network and N is the number of neurons.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
brunel94PRE.pdf
non disponibili
Descrizione: article
Tipologia:
Pdf editoriale (Publisher's layout)
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
195.81 kB
Formato
Adobe PDF
|
195.81 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.