We study the recognition capabilities of the Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. We show that the recognition capabilities of such a model at zero temperature outperform those of the original Hopfield model, due to a substantial increase of the storage capacity and the lack of a naturally defined basin of attraction. The modified model does not fall abruptly into the regime of complete confusion when memory load exceeds a sharp threshold. This latter circumstance, together with an increase of the storage capacity, renders such a modified Hopfield model a promising candidate for further research, with possible diverse applications.
Recognition capabilities of a Hopfield model with auxiliary hidden neurons / Benedetti, M.; Dotsenko, V.; Fischetti, G.; Marinari, E.; Oshanin, G.. - In: PHYSICAL REVIEW. E. - ISSN 2470-0045. - 103:6(2021). [10.1103/PhysRevE.103.L060401]
Recognition capabilities of a Hopfield model with auxiliary hidden neurons
Benedetti M.;Fischetti G.;Marinari E.
;
2021
Abstract
We study the recognition capabilities of the Hopfield model with auxiliary hidden layers, which emerge naturally upon a Hubbard-Stratonovich transformation. We show that the recognition capabilities of such a model at zero temperature outperform those of the original Hopfield model, due to a substantial increase of the storage capacity and the lack of a naturally defined basin of attraction. The modified model does not fall abruptly into the regime of complete confusion when memory load exceeds a sharp threshold. This latter circumstance, together with an increase of the storage capacity, renders such a modified Hopfield model a promising candidate for further research, with possible diverse applications.File | Dimensione | Formato | |
---|---|---|---|
Benedetti_Recognition capabilities_2021.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
612.95 kB
Formato
Adobe PDF
|
612.95 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.