Sciweavers

Share
ICAISC
2010
Springer

Canonical Correlation Analysis for Multiview Semisupervised Feature Extraction

9 years 3 months ago
Canonical Correlation Analysis for Multiview Semisupervised Feature Extraction
Hotelling’s Canonical Correlation Analysis (CCA) works with two sets of related variables, also called views, and its goal is to find their linear projections with maximal mutual correlation. CCA is most suitable for unsupervised feature extraction when given two views but it has been also long known that in supervised learning when there is only a single view of data given, the supervision signal (classlabels) can be given to CCA as the second view and CCA simply reduces to Fisher’s Linear Discriminant Analysis (LDA). However, it is unclear how to use this equivalence for extracting features from multiview data in semisupervised setting (i.e. what modification to the CCA mechanism could incorporate the class-labels along with the two views of the data when labels of some samples are unknown). In this paper, a CCA-based method supplemented by the essence of LDA is proposed for semi-supervised feature extraction from multiview data.
Olcay Kursun, Ethem Alpaydin
Added 12 Oct 2010
Updated 12 Oct 2010
Type Conference
Year 2010
Where ICAISC
Authors Olcay Kursun, Ethem Alpaydin
Comments (0)
books