A spectral approach to Hebbian-like neural networks

Elena Agliari, Alberto Fachechi and Domenico Luongo

Applied Mathematics and Computation, 2024, vol. 474, issue C

Abstract: We consider the Hopfield neural network as a model of associative memory and we define its neuronal interaction matrix J as a function of a set of K×M binary vectors {ξμ,A}μ=1,...,KA=1,...,M representing a sample of the reality that we want to retrieve. In particular, any item ξμ,A is meant as a corrupted version of an unknown ground pattern ζμ, that is the target of our retrieval process. We consider and compare two definitions for J, referred to as supervised and unsupervised, according to whether the class μ, each example belongs to, is unveiled or not, also, these definitions recover the paradigmatic Hebb's rule under suitable limits. The spectral properties of the resulting matrices are studied and used to inspect the retrieval capabilities of the related models as a function of their control parameters.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0096300324001619
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:apmaco:v:474:y:2024:i:c:s0096300324001619

DOI: 10.1016/j.amc.2024.128689

Access Statistics for this article

Applied Mathematics and Computation is currently edited by Theodore Simos

More articles in Applied Mathematics and Computation from Elsevier
Bibliographic data for series maintained by Catherine Liu ().