dor_id: 41381

506.#.#.a: Público

590.#.#.d: Los artículos enviados a la Revista Mexicana de Física se someten a un estricto proceso de revisión llevado a cabo por árbitros anónimos, independientes y especializados en todo el mundo.

510.0.#.a: Consejo Nacional de Ciencia y Tecnología (CONACyT), Sistema Regional de Información en Línea para Revistas Científicas de América Latina, el Caribe, España y Portugal (Latindex), Scientific Electronic Library Online (SciELO), SCOPUS, Web Of Science (WoS)

561.#.#.u: http://www.fciencias.unam.mx/

650.#.4.x: Físico Matemáticas y Ciencias de la Tierra

336.#.#.b: info:eu-repo/semantics/article

336.#.#.3: Artículo de Investigación

336.#.#.a: Artículo

351.#.#.6: http://revistas.unam.mx/index.php/rmf

351.#.#.b: Revista Mexicana de Física

351.#.#.a: Artículos

harvesting_group: RevistasUNAM

270.1.#.p: Revistas UNAM. Dirección General de Publicaciones y Fomento Editorial, UNAM en revistas@unam.mx

590.#.#.c: Open Journal Systems (OJS)

270.#.#.d: MX

270.1.#.d: México

590.#.#.b: Concentrador

883.#.#.u: http://www.revistas.unam.mx/front/

883.#.#.a: Revistas UNAM

590.#.#.a: Coordinación de Difusión Cultural

883.#.#.1: http://www.publicaciones.unam.mx/

883.#.#.q: Dirección General de Publicaciones y Fomento Editorial, UNAM

850.#.#.a: Universidad Nacional Autónoma de México

856.4.0.u: http://revistas.unam.mx/index.php/rmf/article/view/14226/13563

100.1.#.a: Barrón Fernández, R.; Sossa Anzuela, J. H.

524.#.#.a: Barrón Fernández, R., et al. (2007). Extended αβ associative memories. Revista Mexicana de Física; Vol 53, No 001. Recuperado de https://repositorio.unam.mx/contenidos/41381

245.1.0.a: Extended αβ associative memories

502.#.#.c: Universidad Nacional Autónoma de México

561.1.#.a: Facultad de Ciencias, UNAM

264.#.0.c: 2007

264.#.1.c: 2007-01-01

653.#.#.a: Computer science and technology; neural engineering; image quality; contrast; resolution; noise

506.1.#.a: La titularidad de los derechos patrimoniales de esta obra pertenece a las instituciones editoras. Su uso se rige por una licencia Creative Commons BY-NC-ND 4.0 Internacional, https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.es, fecha de asignación de la licencia 2007-01-01, para un uso diferente consultar al responsable jurídico del repositorio por medio de rmf@ciencias.unam.mx

884.#.#.k: http://revistas.unam.mx/index.php/rmf/article/view/14226

041.#.7.h: eng

520.3.#.a: The αβ associative memories recently developed in Ref. 10 have proven to be powerful tools for memorizing and recalling patterns when they appear distorted by noise. However they are only useful in the binary case. In this paper we show that it is possible to extend these memories now to the gray-level case. To get the desired extension, we take the original operators α and β, foundation of the αβ memories, and propose a more general family of operators. We find that the original operators α and β are a subset of these extended operators. For this we first formulate a set of functional equations in terms of the original properties of operators α and β. Next we solve this system of equations and find a family of solutions. We show that the α and β originally proposed in Ref. 10 are just a particular case of this new family. We present the properties of the new operators. We then use these operators to build a new set of extended memories. We also give the conditions under which the extended memories are able to recall a pattern either from the pattern’s fundamental set or from altered versions of them. We give real examples with images where the proposed memories show their efficiency. We compare the proposal with other similar works, and show the ours performs much better.

773.1.#.t: Revista Mexicana de Física; Vol 53, No 001 (2007)

773.1.#.o: http://revistas.unam.mx/index.php/rmf

046.#.#.j: 2020-11-25 00:00:00.000000

022.#.#.a: 2683-2224 (digital); 0035-001X (impresa)

310.#.#.a: Bimestral

264.#.1.b: Sociedad Mexicana de Física, A.C.

758.#.#.1: http://revistas.unam.mx/index.php/rmf

handle: 00ef260ade9f1dee

harvesting_date: 2020-09-23 00:00:00.0

856.#.0.q: application/pdf

last_modified: 2020-11-27 00:00:00

license_url: https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode.es

license_type: by-nc-nd

_deleted_conflicts: 6-82ef48e419e34447ffc4bd427d7f8bd6,2-30f3fe9368e58465859b1ac311fb57f3

No entro en nada

No entro en nada 2

Artículo

Extended αβ associative memories

Barrón Fernández, R.; Sossa Anzuela, J. H.

Facultad de Ciencias, UNAM, publicado en Revista Mexicana de Física, y cosechado de Revistas UNAM

Licencia de uso

Procedencia del contenido

Entidad o dependencia
Facultad de Ciencias, UNAM
Revista
Repositorio
Contacto
Revistas UNAM. Dirección General de Publicaciones y Fomento Editorial, UNAM en revistas@unam.mx

Cita

Barrón Fernández, R., et al. (2007). Extended αβ associative memories. Revista Mexicana de Física; Vol 53, No 001. Recuperado de https://repositorio.unam.mx/contenidos/41381

Descripción del recurso

Autor(es)
Barrón Fernández, R.; Sossa Anzuela, J. H.
Tipo
Artículo de Investigación
Área del conocimiento
Físico Matemáticas y Ciencias de la Tierra
Título
Extended αβ associative memories
Fecha
2007-01-01
Resumen
The αβ associative memories recently developed in Ref. 10 have proven to be powerful tools for memorizing and recalling patterns when they appear distorted by noise. However they are only useful in the binary case. In this paper we show that it is possible to extend these memories now to the gray-level case. To get the desired extension, we take the original operators α and β, foundation of the αβ memories, and propose a more general family of operators. We find that the original operators α and β are a subset of these extended operators. For this we first formulate a set of functional equations in terms of the original properties of operators α and β. Next we solve this system of equations and find a family of solutions. We show that the α and β originally proposed in Ref. 10 are just a particular case of this new family. We present the properties of the new operators. We then use these operators to build a new set of extended memories. We also give the conditions under which the extended memories are able to recall a pattern either from the pattern’s fundamental set or from altered versions of them. We give real examples with images where the proposed memories show their efficiency. We compare the proposal with other similar works, and show the ours performs much better.
Tema
Computer science and technology; neural engineering; image quality; contrast; resolution; noise
Idioma
eng
ISSN
2683-2224 (digital); 0035-001X (impresa)

Enlaces