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.authorCarlos Segura, Enrique-
dc.identifier.citationRevista Computación y Sistemas; Vol. 13 No. 2es
dc.description.abstractAbstract 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.sponsorshipInstituto Politécnico Nacional - Centro de Investigación en Computación (CIC).es
dc.publisherRevista Computación y Sistemas; Vol. 13 No. 2es
dc.relation.ispartofseriesRevista Computación y Sistemas;Vol. 13 No. 2-
dc.subjectKeywords. associative memory, continuous metric space, dynamical systems, Hopfield model, stability, Glauber dynamics, continuous topology.es
dc.titleAssociative Memory in a Continuous Metric Space: A Theoretical Foundationes
dc.title.alternativeMemoria Asociativa en un Espacio M etrico Continuo: Fundamentos Te oricoses
dc.description.especialidadInvestigación en Computaciónes
Aparece en las colecciones: Revistas

Ficheros en este ítem:
Fichero Descripción Tamaño Formato  
v13no2_Art03.pdf1.52 MBAdobe PDFVisualizar/Abrir

Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.