A network for recursive extraction of canonical coordinates

A 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 algo...

Full description

Saved in:
Bibliographic Details
Published inNeural networks Vol. 16; no. 5; pp. 801 - 808
Main Authors Pezeshki, Ali, Azimi-Sadjadi, Mahmood R., Scharf, Louis L.
Format Journal Article Conference Proceeding
LanguageEnglish
Published Oxford Elsevier Ltd 01.06.2003
Elsevier Science
Subjects
Applied sciences
Artificial intelligence
Canonical coordinates
Computer science; control theory; systems
Connectionism. Neural networks
Deflation
Exact sciences and technology
Information Systems
Iterative learning
Neural Networks (Computer)
Singular value decomposition
Canonical coordinates
Deflation
Iterative learning
Singular value decomposition
Online AccessGet full text

Cover

More Information
Summary:A 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0893-6080
1879-2782
DOI:10.1016/S0893-6080(03)00112-6