The Hopfield model and the Boltzmann machine are among the most popular examples of neural networks. The latter, widely used for classification and feature detection, is able to efficiently learn a generative model from observed data and constitutes the benchmark for statistical learning. The former, designed to mimic the retrieval phase of an artificial associative memory lays in between two paradigmatic statistical mechanics models, namely the Curie-Weiss and the Sherrington-Kirkpatrick, which are recovered as the limiting cases of, respectively, one and many stored memories. Interestingly, the Boltzmann machine and the Hopfield network, if considered to be two cognitive processes (learning and information retrieval), are nothing more than two sides of the same coin. In fact, it is possible to exactly map the one into the other. We will inspect such an equivalence retracing the most representative steps of the research in this field.
Boltzmann machines as generalized hopfield networks: A review of recent results and outlooks / Marullo, C.; Agliari, E.. - In: ENTROPY. - ISSN 1099-4300. - 23:1(2021), pp. 1-16. [10.3390/e23010034]
Boltzmann machines as generalized hopfield networks: A review of recent results and outlooks
Marullo C.Primo
;Agliari E.
Ultimo
2021
Abstract
The Hopfield model and the Boltzmann machine are among the most popular examples of neural networks. The latter, widely used for classification and feature detection, is able to efficiently learn a generative model from observed data and constitutes the benchmark for statistical learning. The former, designed to mimic the retrieval phase of an artificial associative memory lays in between two paradigmatic statistical mechanics models, namely the Curie-Weiss and the Sherrington-Kirkpatrick, which are recovered as the limiting cases of, respectively, one and many stored memories. Interestingly, the Boltzmann machine and the Hopfield network, if considered to be two cognitive processes (learning and information retrieval), are nothing more than two sides of the same coin. In fact, it is possible to exactly map the one into the other. We will inspect such an equivalence retracing the most representative steps of the research in this field.File | Dimensione | Formato | |
---|---|---|---|
Marullo_Boltzmann-Machines_2021.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.28 MB
Formato
Adobe PDF
|
2.28 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.