Networks of neural networks: more is different

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Agliari, Elena, Alessandrelli, Andrea, Barra, Adriano, Centonze, Martino Salomone, Ricci-Tersenghi, Federico
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911210256990208
author Agliari, Elena
Alessandrelli, Andrea
Barra, Adriano
Centonze, Martino Salomone
Ricci-Tersenghi, Federico
author_facet Agliari, Elena
Alessandrelli, Andrea
Barra, Adriano
Centonze, Martino Salomone
Ricci-Tersenghi, Federico
contents The common thread behind the recent Nobel Prize in Physics to John Hopfield and those conferred to Giorgio Parisi in 2021 and Philip Anderson in 1977 is disorder. Quoting Philip Anderson: "more is different". This principle has been extensively demonstrated in magnetic systems and spin glasses, and, in this work, we test its validity on Hopfield neural networks to show how an assembly of these models displays emergent capabilities that are not present at a single network level. Such an assembly is designed as a layered associative Hebbian network that, beyond accomplishing standard pattern recognition, spontaneously performs also pattern disentanglement. Namely, when inputted with a composite signal -- e.g., a musical chord -- it can return the single constituting elements -- e.g., the notes making up the chord. Here, restricting to notes coded as Rademacher vectors and chords that are their mixtures (i.e., spurious states), we use tools borrowed from statistical mechanics of disordered systems to investigate this task, obtaining the conditions over the model control-parameters such that pattern disentanglement is successfully executed.
format Preprint
id arxiv_https___arxiv_org_abs_2501_16789
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Networks of neural networks: more is different
Agliari, Elena
Alessandrelli, Andrea
Barra, Adriano
Centonze, Martino Salomone
Ricci-Tersenghi, Federico
Disordered Systems and Neural Networks
Statistical Mechanics
Mathematical Physics
The common thread behind the recent Nobel Prize in Physics to John Hopfield and those conferred to Giorgio Parisi in 2021 and Philip Anderson in 1977 is disorder. Quoting Philip Anderson: "more is different". This principle has been extensively demonstrated in magnetic systems and spin glasses, and, in this work, we test its validity on Hopfield neural networks to show how an assembly of these models displays emergent capabilities that are not present at a single network level. Such an assembly is designed as a layered associative Hebbian network that, beyond accomplishing standard pattern recognition, spontaneously performs also pattern disentanglement. Namely, when inputted with a composite signal -- e.g., a musical chord -- it can return the single constituting elements -- e.g., the notes making up the chord. Here, restricting to notes coded as Rademacher vectors and chords that are their mixtures (i.e., spurious states), we use tools borrowed from statistical mechanics of disordered systems to investigate this task, obtaining the conditions over the model control-parameters such that pattern disentanglement is successfully executed.
title Networks of neural networks: more is different
topic Disordered Systems and Neural Networks
Statistical Mechanics
Mathematical Physics
url https://arxiv.org/abs/2501.16789