EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Pattern disentanglement and reconstruction by modular Hebbian networks

Elena Agliari, Shahed Akter, Andrea Alessandrelli, Alberto Fachechi

Bollettino dell'Unione Matematica Italiana · 28.07.2026

DOI: 10.1007/s40574-026-00538-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bollettino dell'Unione Matematica Italiana, online erschienen am 28.07.2026. Verfasst von Elena Agliari und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministero dell’Istruzione, dell’Università e della Ricerca.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We address the problem of reconstructing a set of K binary patterns $$\varvec{\Xi }= (\varvec{\xi }^1,..., \varvec{\xi }^K) \in \{-1, +1 \}^{N \times K}$$ Ξ = ( ξ 1 , . . . , ξ K ) ∈ { - 1 , + 1 } N × K , starting from their covariance matrix $$\varvec{\Xi }\varvec{\Xi }^T$$ Ξ Ξ T and from a set of mixtures of the form $$\varvec{\sigma }_M= \text {sign}(\sum _{\mu \in \mathcal {S}_M \subseteq \{1,..., K\}} \varvec{\xi }^{\mu })$$ σ M = sign ( ∑ μ ∈ S M ⊆ { 1 , . . . , K } ξ μ ) , with $$\left\lvert S_M\right\rvert =M$$ S M = M . To this aim, we engage a modular Hebbian network, specified by the interaction matrix $$\varvec{J}^H = \frac{1}{N}\varvec{\Xi }\varvec{\Xi }^T$$ J H = 1 N Ξ Ξ T , where $${\varvec{\sigma }_M}$$ σ M is taken as the initial state, repeated in each of the constituting L modules and the stable state resulting from a Gibbs evolution rule is taken as an L -tuple of candidate patterns. Finally, by properly handling $$\varvec{J}^H$$ J H we can derive the projector matrix $$\varvec{J}^K = \varvec{\Xi }(\varvec{\Xi }^T \varvec{\Xi })^{-1} \varvec{\Xi }^T$$ J K = Ξ ( Ξ T Ξ ) - 1 Ξ T by which we can determine whether these candidate patterns are a good estimate for the ground patterns.

Förderung

  • Ministero dell’Istruzione, dell’Università e della Ricerca

Zitieren

APA

Agliari, E., Akter, S., Alessandrelli, A., & Fachechi, A. (2026). Pattern disentanglement and reconstruction by modular Hebbian networks. Bollettino dell'Unione Matematica Italiana. https://doi.org/10.1007/s40574-026-00538-2

Vancouver

Agliari E, Akter S, Alessandrelli A, Fachechi A. Pattern disentanglement and reconstruction by modular Hebbian networks. Bollettino dell'Unione Matematica Italiana. 2026. doi:10.1007/s40574-026-00538-2

BibTeX
@article{Agliari2026,
  author = {Agliari, Elena and Akter, Shahed and Alessandrelli, Andrea and Fachechi, Alberto},
  title = {Pattern disentanglement and reconstruction by modular Hebbian networks},
  journal = {Bollettino dell'Unione Matematica Italiana},
  year = {2026},
  doi = {10.1007/s40574-026-00538-2}
}
Kostenlos starten →