We consider the Hopfield neural network as a model of associative memory and we define its neuronal interaction matrix $\bb J$ as a function of a set of $K \times M$ binary vectors $\{\bb \xi^{\mu, A} \}_{\mu=1,...,K}^{A=1,...,M}$ representing a sample of the reality that we want to retrieve. In particular, any item $\bb \xi^{\mu, A}$ is meant as a corrupted version of an unknown ground pattern $\bb \zeta^{\mu}$, that is the target of our retrieval process. We consider and compare two definitions for $\bb J$, referred to as supervised and unsupervised, according to whether the class $\mu$, 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.
A spectral approach to Hebbian-like neural networks / Agliari, Elena; Fachechi, Alberto; Luongo, Domenico. - In: APPLIED MATHEMATICS AND COMPUTATION. - ISSN 0096-3003. - 474:(2024). [10.1016/j.amc.2024.128689]
A spectral approach to Hebbian-like neural networks
Agliari, Elena
;Fachechi, Alberto;Luongo, Domenico
2024
Abstract
We consider the Hopfield neural network as a model of associative memory and we define its neuronal interaction matrix $\bb J$ as a function of a set of $K \times M$ binary vectors $\{\bb \xi^{\mu, A} \}_{\mu=1,...,K}^{A=1,...,M}$ representing a sample of the reality that we want to retrieve. In particular, any item $\bb \xi^{\mu, A}$ is meant as a corrupted version of an unknown ground pattern $\bb \zeta^{\mu}$, that is the target of our retrieval process. We consider and compare two definitions for $\bb J$, referred to as supervised and unsupervised, according to whether the class $\mu$, 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.File | Dimensione | Formato | |
---|---|---|---|
Agliari_A- spectral-approach_2024.pdf
accesso aperto
Note: Agliari_A- spectral-approach_2024
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Creative commons
Dimensione
1.07 MB
Formato
Adobe PDF
|
1.07 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.