Multiview Bayesian correlated component analysis

DOI10.1162/NECO_A_00774zbMATH Open1414.92175DBLPjournals/neco/KamronnPH15arXiv1802.02343WikidataQ28912373 ScholiaQ28912373MaRDI QIDQ5380337FDOQ5380337

Authors: Simon Kamronn, Andreas Trier Poulsen, Lars Kai Hansen 

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Abstract: 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.

Full work available at URL: https://arxiv.org/abs/1802.02343

Recommendations

• Bayesian canonical correlation analysis
• Functional multiple-set canonical correlation analysis
• Correlated topographic analysis: estimating an ordering of correlated components
• A learning algorithm for adaptive canonical correlation analysis of several data sets
• Orthogonal connectivity factorization: interpretable decomposition of variability in correlation matrices

zbMATH Keywords

EEG dataBayesian correlated component analysisbrain process similarity

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Neural biology (92C20) Biomedical imaging and signal processing (92C55)

Cites Work

• Pattern recognition and machine learning.
• Machine learning. A probabilistic perspective
• RELATIONS BETWEEN TWO SETS OF VARIATES
• Probabilistic Principal Component Analysis
• Variational message passing
• Pruning from Adaptive Regularization
• Bayesian canonical correlation analysis

Cited In (4)

• Bayesian canonical correlation analysis
• Title not available (Why is that?)
• A Bayesian approach to multi-view 4D modeling
• Correlated topographic analysis: estimating an ordering of correlated components

Uses Software

• Infer.NET
• PMTK
• PRMLT

This page was built for publication: Multiview Bayesian correlated component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380337)