Adaptive diagonalization for canonical correlation analysis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Canonical correlation analysis is an essential technique in many fields such as multivariate statistical analysis and signal processing. In this paper, un-constrained optimization criteria for extracting the actual canonical correlation coordinates are proposed. The resulting gradient dynamical system is thoroughly analyzed in terms of stability and the limiting behavior of the system as t → ∞. One of the main features of this approach is that orthogonal basis for canonical variates which diagonalizes the coherence matrix is automatically obtained. A numerical example is included to demonstrate the performance of the proposed algorithm.

Original languageEnglish (US)
Title of host publicationThe 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
Pages1906-1911
Number of pages6
DOIs
StatePublished - Dec 1 2007
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: Aug 12 2007Aug 17 2007

Publication series

NameIEEE International Conference on Neural Networks - Conference Proceedings
ISSN (Print)1098-7576

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period8/12/078/17/07

Fingerprint Dive into the research topics of 'Adaptive diagonalization for canonical correlation analysis'. Together they form a unique fingerprint.

Cite this