Ensemble of diluted attractor networks with optimized topology for fingerprint retrieval
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
ElsevierDate
2021-03-02Citation
10.1016/j.neucom.2021.02.033
Neurocomputing 442 (2021): 269-280
ISSN
0925-2312DOI
10.1016/j.neucom.2021.02.033Funded by
This work was funded by and UDLA-SIS.MGR.20.01. This research was also funded by the Spanish Ministry of Science and Innovation/FEDER, under the \RETOS" Programme, with grant numbers: TIN2017-84452-R and RTI2018-098019-B-I00; and by the CYTED Network \Ibero-American Thematic Network on ICT Applications for Smart Cities", grant number: 518RT0559.Project
Gobierno de España. TIN2017-84452-R; Gobierno de España. RTI2018-098019-B-I00Editor's Version
https://doi.org/10.1016/j.neucom.2021.02.033Subjects
Attractor neural networks; Ensemble of diluted modules; Structured patterns; Module input optimization,; Module specialization; Fingerprint retrieval; Information performance metrics; InformáticaRights
2021 Elsevier B.V .Al lrights reserved.Esta obra está bajo una licencia de Creative Commons Reconocimiento-NoComercial-SinObraDerivada 4.0 Internacional.
Abstract
The present study analyzes the retrieval capacity of an Ensemble of diluted Attractor Neural Networks for real patterns (i.e., non-random ones), as it is the case of human fingerprints. We explore the optimal number of Attractor Neural Networks in the ensemble to achieve a maximum fingerprint storage capacity. The retrieval performance of the ensemble is measured in terms of the network connectivity structure, by comparing 1D ring to 2D cross grid topologies for the random shortcuts ratio. Given the nature of the network ensemble and the different characteristics of patterns, an optimization can be carried out considering how the pattern subsets are assigned to the ensemble modules. The ensemble specialization splitting into several modules of attractor networks is explored with respect to the activities of patterns and also in terms of correlations of the subsets of patterns assigned to each module in the ensemble network.
Files in this item
Google Scholar:González Rodríguez, Mario Salvador
-
Sánchez Calle, Ángel
-
Domínguez Carreta, David Renato
-
Rodríguez Ortiz, Francisco Borja
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.