Multi-View Bayesian Correlated Component Analysis
This work addresses the need for more flexible analysis of brain process similarity across subjects, though it appears incremental as it builds on existing correlated component analysis methods.
The authors tackled the problem of inferring the level of universality in multi-view brain data, proposing a hierarchical probabilistic model that ranges from unrelated to identical representations, and validated it with simulated data and an EEG benchmark dataset.
Correlated component analysis as proposed by Dmochowski et al. (2012) is a tool for investigating brain process similarity in the responses to multiple views of a given stimulus. Correlated components are identified under the assumption that the involved spatial networks are identical. Here we propose a hierarchical probabilistic model that can infer the level of universality in such multi-view data, from completely unrelated representations, corresponding to canonical correlation analysis, to identical representations as in correlated component analysis. This new model, which we denote Bayesian correlated component analysis, evaluates favourably against three relevant algorithms in simulated data. A well-established benchmark EEG dataset is used to further validate the new model and infer the variability of spatial representations across multiple subjects.