Title :
Variational Bayesian Approach to Canonical Correlation Analysis
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing
fDate :
6/29/1905 12:00:00 AM
Abstract :
As a dimension reduction algorithm, canonical correlation analysis (CCA) encounters the issue of selecting the number of canonical correlations. In this letter, we present a Bayesian model selection algorithm for CCA based on a probabilistic interpretation. A hierarchical Bayesian model is applied to probabilistic CCA and learned by variational approximation. This method not only estimates the model parameters, but also automatically determines the number of canonical correlations and avoids overfitting. Experiments show that it performs better compared with maximum likelihood and some other model selection methods
Keywords :
Bayes methods; parameter estimation; variational techniques; Bayesian model selection algorithm; canonical correlation analysis; dimension reduction algorithm; maximum likelihood; model parameter estimation; variational Bayesian approach; variational approximation; Algorithm design and analysis; Bayesian methods; Covariance matrix; Equations; Gaussian distribution; Maximum likelihood estimation; Neural networks; Parameter estimation; Plasmas; Bayesian inference; canonical correlation analysis (CCA); dimensionality reduction; model selection; variational approximation; Algorithms; Artificial Intelligence; Bayes Theorem; Computer Simulation; Decision Support Techniques; Information Storage and Retrieval; Models, Statistical; Neural Networks (Computer); Pattern Recognition, Automated; Statistics as Topic;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2007.891186
