We consider dense, associative neural-networks trained with no supervision and we investigate their computational capabilities analytically, via statistical-mechanics tools, and numerically, via Monte Carlo simulations. In particular, we obtain a phase diagram summarizing their performance as a function of the control parameters (e.g. quality and quantity of the training dataset, network storage, noise) that is valid in the limit of large network size and structureless datasets. Moreover, we establish a bridge between macroscopic observables standardly used in statistical mechanics and loss functions typically used in the machine learning. As technical remarks, from the analytical side, we extend Guerra’s interpolation to tackle the non-Gaussian distributions involved in the post-synaptic potentials while, from the computational counterpart, we insert Plefka’s approximation in the Monte Carlo scheme, to speed up the evaluation of the synaptic tensor, overall obtaining a novel and broad approach to investigate unsupervised learning in neural networks, beyond the shallow limit.
Dense Hebbian neural networks: A replica symmetric picture of unsupervised learning / Agliari, E.; Albanese, L.; Alemanno, F.; Alessandrelli, A.; Barra, A.; Giannotti, F.; Lotito, D.; Pedreschi, D.. - In: PHYSICA. A. - ISSN 0378-4371. - 627:(2023), p. 129143. [10.1016/j.physa.2023.129143]
Dense Hebbian neural networks: A replica symmetric picture of unsupervised learning
Agliari E.;Barra A.;
2023
Abstract
We consider dense, associative neural-networks trained with no supervision and we investigate their computational capabilities analytically, via statistical-mechanics tools, and numerically, via Monte Carlo simulations. In particular, we obtain a phase diagram summarizing their performance as a function of the control parameters (e.g. quality and quantity of the training dataset, network storage, noise) that is valid in the limit of large network size and structureless datasets. Moreover, we establish a bridge between macroscopic observables standardly used in statistical mechanics and loss functions typically used in the machine learning. As technical remarks, from the analytical side, we extend Guerra’s interpolation to tackle the non-Gaussian distributions involved in the post-synaptic potentials while, from the computational counterpart, we insert Plefka’s approximation in the Monte Carlo scheme, to speed up the evaluation of the synaptic tensor, overall obtaining a novel and broad approach to investigate unsupervised learning in neural networks, beyond the shallow limit.File | Dimensione | Formato | |
---|---|---|---|
Agliari_Dense-Hebbian_2023b.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
1.9 MB
Formato
Adobe PDF
|
1.9 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.