Stochastic Processes for Canonical Correlation Analysis

We consider two stochastic process methods for performing canonical correlation analysis (CCA). The first uses a Gaussian Process formulation of regression in which we use the current projection of one data set as the target for the other and then repeat in the opposite direction. The second uses a Dirichlet process of Gaussian models where the Gaussian models are determined by Probabilistic CCA [1]. The latter method is more computationally intensive but has the advantages of non-parametric approaches.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Colin Fyfe, Gayle Leen
• Keywords: ESANN 2006, ESANN 2007, Gaussian Models, Gaussian Process Formulation, Stochastic Process Methods