Extracting coactivated features from multiple data sets

Authors:
Michael U. Gutmann;Aapo Hyvärinen
Affiliations:
Dept. of Computer Science and HIIT, Dept. of Mathematics and Statistics, University of Helsinki, Finland;Dept. of Computer Science and HIIT, Dept. of Mathematics and Statistics, University of Helsinki, Finland
Venue:
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Year:
2011

Citing 4
Cited 2

Simple-cell-like receptive fields maximize temporal coherence in natural video

Neural Computation
Extending ICA for finding jointly dependent components from two related data sets

Neurocomputing
Mixtures of robust probabilistic principal component analyzers

Neurocomputing
Probabilistic approach to detecting dependencies between data sets

Neurocomputing

A canonical correlation analysis based method for improving BSS of two related data sets

LVA/ICA'12 Proceedings of the 10th international conference on Latent Variable Analysis and Signal Separation
Finding dependent and independent components from related data sets: A generalized canonical correlation analysis based method

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a nonlinear generalization of Canonical Correlation Analysis (CCA) to find related structure in multiple data sets. The new method allows to analyze an arbitrary number of data sets, and the extracted features capture higher-order statistical dependencies. The features are independent components that are coupled across the data sets. The coupling takes the form of coactivation (dependencies of variances). We validate the new method on artificial data, and apply it to natural images and brain imaging data.