Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Sparsely Connected Hopfield Networks for the Recognition of Correlated Pattern Sets

Title: Sparsely Connected Hopfield Networks for the Recognition of Correlated Pattern Sets
Authors: Thomas Stiefvater; Klaus-Robert Müller; Herbert Janßen; M.P.W. Lasec
Contributors: The Pennsylvania State University CiteSeerX Archives
Source: http://www.first.gmd.de/persons/Mueller.Klaus-Robert/Network93.ps.gz.
Collection: CiteSeerX
Description: A sparsely connected Hopfield network for the recognition of natural, highly correlated video images is proposed. A general design mechanism for the construction of a local neighbourhood structure using a statistical analysis of an arbitrary given pattern set is suggested. The duality between learning and dilution is employed and different learning respectively dilution schemes are discussed. The practical use and the efficiency of the model are shown in simulations of a large network (N=12288). We use a set of natural patterns with high inter pattern correlations and a high site correlation within each pattern, in which the correlations are given and not constructed by special rules as for highly correlated random pattern sets. The results obtained are analysed for different coding types of the binary pattern set. 1 Introduction Up to now Hopfield networks have mostly been investigated in the context of statistical mechanics for random patterns [1, 2, 5]. In this work we would like.
Document Type: text
File Description: application/postscript
Language: English
Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.54.9100
Availability: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.54.9100; http://www.first.gmd.de/persons/Mueller.Klaus-Robert/Network93.ps.gz
Rights: Metadata may be used without restrictions as long as the oai identifier remains attached to it.
Accession Number: edsbas.9BEC9BFC
Database: BASE