The Capacity of Modern Hopfield Networks under the Data Manifold Hypothesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Achilli, Beatrice, Ambrogioni, Luca, Lucibello, Carlo, Mézard, Marc, Ventura, Enrico
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909535792267264
author Achilli, Beatrice
Ambrogioni, Luca
Lucibello, Carlo
Mézard, Marc
Ventura, Enrico
author_facet Achilli, Beatrice
Ambrogioni, Luca
Lucibello, Carlo
Mézard, Marc
Ventura, Enrico
contents We generalize the computation of the capacity of exponential Hopfield model from Lucibello and Mézard (2024) to more generic pattern ensembles, including binary patterns and patterns generated from a hidden manifold model.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Capacity of Modern Hopfield Networks under the Data Manifold Hypothesis
Achilli, Beatrice
Ambrogioni, Luca
Lucibello, Carlo
Mézard, Marc
Ventura, Enrico
Disordered Systems and Neural Networks
We generalize the computation of the capacity of exponential Hopfield model from Lucibello and Mézard (2024) to more generic pattern ensembles, including binary patterns and patterns generated from a hidden manifold model.
title The Capacity of Modern Hopfield Networks under the Data Manifold Hypothesis
topic Disordered Systems and Neural Networks
url https://arxiv.org/abs/2503.09518