Analysis of the Sanger Hebbian Neural Network

dc.contributor.authorBerzal, José Andrés
dc.contributor.authorZufiria, Pedro
dc.date.accessioned2024-02-09T10:03:28Z
dc.date.available2024-02-09T10:03:28Z
dc.date.issued2005
dc.descriptionUtilización de Redes Neuronales de Sanger para el Análisis de Componentes Principales de forma adaptativa según los datos de a procesar. En Análisis de Componente Principales es un algoritmo básico en la ciencia del dato, comunicaciones y procesamiento de señal. Se realiza el análisis dinámico de estas Redes Neuronales aplicando escalas temporales y se llega a establecer una relación entre el dato a procesar y la velocidad de convergencia.es
dc.description.abstractIn this paper, the behavior of the Sanger hebbian artificial neural networks is analyzed. Hebbian neural networks are employed in communications and signal processing applications, among others, due to their capability to implement Principal Component Analysis (PCA). Different improvements over the original model due to Oja have been developed in the last two decades. Among them, Sanger model was designed to directly provide the eigenvectors of the correlation matrix. The behavior of these models has been traditionally considered on a continuous-time formulation whose validity is justified via some analytical procedures that presume, among other hypotheses, an specific asymptotic behavior of the learning gain. In practical applications, these assumptions cannot be guaranteed. This paper addresses the study of a deterministic discrete-time (DDT) formulation that characterizes the average evolution of the net, preserving the discrete-time form of the original network and gathering a more realistic behavior of the learning gain. The dynamics behavior Sanger model is analyzed in this more realistic context. The results thoroughly characterize the relationship between the learning gain and the eigenvalue structure of the correlation matrix.es
dc.identifier.citationBerzal, J.A., Zufiria, P.J. (2005). Analysis of the Sanger Hebbian Neural Network. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_2es
dc.identifier.doi10.1007/11494669es
dc.identifier.issn978-3-540-26208-4
dc.identifier.issn978-3-540-32106-4
dc.identifier.urihttps://hdl.handle.net/10115/30214
dc.language.isoenges
dc.publisherSpringer, Berlin, Heidelberges
dc.rights.accessRightsinfo:eu-repo/semantics/restrictedAccesses
dc.subjectNeural Networkses
dc.subjectLearning ratees
dc.subjectLearning gaines
dc.subjectStochastic approximation algorithmes
dc.subjectShort Range Forecastes
dc.subjectArtificial Intelligence Algorithmses
dc.titleAnalysis of the Sanger Hebbian Neural Networkes
dc.typeinfo:eu-repo/semantics/bookPartes

Archivos

Bloque original

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
sanger.pdf
Tamaño:
193.21 KB
Formato:
Adobe Portable Document Format
Descripción:
Artículo principal

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
2.67 KB
Formato:
Item-specific license agreed upon to submission
Descripción: