Por favor, use este identificador para citar o enlazar este ítem:
http://repositoriodigital.ipn.mx/handle/123456789/15500
Registro completo de metadatos
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Carlos Segura, Enrique | - |
dc.date.accessioned | 2013-04-30T01:07:12Z | - |
dc.date.available | 2013-04-30T01:07:12Z | - |
dc.date.issued | 2009-10-15 | - |
dc.identifier.citation | Revista Computación y Sistemas; Vol. 13 No. 2 | es |
dc.identifier.issn | 1405-5546 | - |
dc.identifier.uri | http://www.repositoriodigital.ipn.mx/handle/123456789/15500 | - |
dc.description.abstract | Abstract We introduce a formal theoretical background, which includes theorems and their proofs, for a neural network model with associative memory and continuous topology, i.e. its processing units are elements of a continuous metric space and the state space is Euclidean and infinite dimensional. This approach is intended as a generalization of the previous ones due to Little and Hopfield. The main contribution of the present work is to integrate -and to provide a theoretical background that makes this integration consistent- two levels of continuity: i) continuous response processing units and ii) continuous topology of the neural system, obtaining a more biologically plausible model of associative memory. We present our analysis according to the following sequence of steps: general results concerning attractors and stationary solutions, including a variational approach for the derivation of the energy function; focus on the case of orthogonal memories, proving theorems on stability, size of attraction basins and spurious states; considerations on the problem of resolution, analyzing the more general case of memories that are not orthogonal, and with possible modifications to the synaptic operator; getting back to discrete models, i. e. considering new viewpoints arising from the present continuous approach and examine which of the new results are also valid for the discrete models; discussion about the generalization of the non deterministic, finite temperature dynamics. | es |
dc.description.sponsorship | Instituto Politécnico Nacional - Centro de Investigación en Computación (CIC). | es |
dc.language.iso | en_US | es |
dc.publisher | Revista Computación y Sistemas; Vol. 13 No. 2 | es |
dc.relation.ispartofseries | Revista Computación y Sistemas;Vol. 13 No. 2 | - |
dc.subject | Keywords. associative memory, continuous metric space, dynamical systems, Hopfield model, stability, Glauber dynamics, continuous topology. | es |
dc.title | Associative Memory in a Continuous Metric Space: A Theoretical Foundation | es |
dc.title.alternative | Memoria Asociativa en un Espacio M etrico Continuo: Fundamentos Te oricos | es |
dc.type | Article | es |
dc.description.especialidad | Investigación en Computación | es |
dc.description.tipo | es | |
Aparece en las colecciones: | Revistas |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
v13no2_Art03.pdf | 1.52 MB | Adobe PDF | Visualizar/Abrir |
Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.