Repository logo
 

A network for recursive extraction of canonical coordinates

Simple item page
dc.contributor.authorScharf, Louis L., author
dc.contributor.authorAzimi-Sadjadi, Mahmood, author
dc.contributor.authorPezeshki, Ali, author
dc.contributor.authorElsevier Science Ltd., publisher
dc.date.accessioned2007-01-03T08:10:21Z
dc.date.available2007-01-03T08:10:21Z
dc.date.issued2003
dc.description.abstractA network structure for canonical coordinate decomposition is presented. The network consists of two single-layer linear subnetworks that together extract the canonical coordinates of two data channels. The connection weights of the networks are trained by a stochastic gradient descent learning algorithm. Each subnetwork features a hierarchical set of lateral connections among its outputs. The lateral connections perform a deflation process that subtracts the contributions of the already extracted coordinates from the input data subspace. This structure allows for adding new nodes for extracting additional canonical coordinates without the need for retraining the previous nodes. The performance of the network is evaluated on a synthesized data set.
dc.format.mediumborn digital
dc.format.mediumarticles
dc.identifier.bibliographicCitationPezeshki, Ali, Mahmood R. Azimi-Sadjadi, and Louis L. Scharf, A Network for Recursive Extraction of Canonical Coordinates, Neural Networks 16, no. 5-6 (June-July 2003): [801]-808.
dc.identifier.urihttp://hdl.handle.net/10217/67874
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relation.ispartofFaculty Publications
dc.rights©2003 Elsevier Science Ltd.
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectsingular value decomposition
dc.subjectiterative learning
dc.subjectdeflation
dc.subjectcanonical coordinates
dc.titleA network for recursive extraction of canonical coordinates
dc.typeText

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ECElls00023.pdf
Size:
177.58 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Faculty Publications