Extracting coactivated features from multiple data sets

M. Gutmann; A. Hyvärinen

doi:10.1007/978-3-642-21735-7_40

Extracting coactivated features from multiple data sets

M. Gutmann, A. Hyvärinen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English
Title of host publication	Artificial Neural Networks and Machine Learning – ICANN 2011
Subtitle of host publication	21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I
Editors	T Honkela
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	323-330
Number of pages	8
ISBN (Electronic)	978-3-642-21735-7
ISBN (Print)	978-3-642-21734-0
DOIs	https://doi.org/10.1007/978-3-642-21735-7_40
Publication status	Published - 2011

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	6791
ISSN (Print)	0302-9743

Access to Document

10.1007/978-3-642-21735-7_40

http://link.springer.com/chapter/10.1007%2F978-3-642-21735-7_40

Cite this

Gutmann, M., & Hyvärinen, A. (2011). Extracting coactivated features from multiple data sets. In T. Honkela (Ed.), Artificial Neural Networks and Machine Learning – ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I (pp. 323-330). (Lecture Notes in Computer Science; Vol. 6791). Springer. https://doi.org/10.1007/978-3-642-21735-7_40

Gutmann, M. ; Hyvärinen, A. / Extracting coactivated features from multiple data sets. Artificial Neural Networks and Machine Learning – ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I. editor / T Honkela. Berlin, Heidelberg : Springer, 2011. pp. 323-330 (Lecture Notes in Computer Science).

@inproceedings{f1bf75d164d94a4ab213db2ab1efa94f,

title = "Extracting coactivated features from multiple data sets",

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.",

author = "M. Gutmann and A. Hyv{\"a}rinen",

year = "2011",

doi = "10.1007/978-3-642-21735-7_40",

language = "English",

isbn = "978-3-642-21734-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "323--330",

editor = "T Honkela",

booktitle = "Artificial Neural Networks and Machine Learning – ICANN 2011",

address = "United Kingdom",

}

Gutmann, M & Hyvärinen, A 2011, Extracting coactivated features from multiple data sets. in T Honkela (ed.), Artificial Neural Networks and Machine Learning – ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I. Lecture Notes in Computer Science, vol. 6791, Springer, Berlin, Heidelberg, pp. 323-330. https://doi.org/10.1007/978-3-642-21735-7_40

Extracting coactivated features from multiple data sets. / Gutmann, M.; Hyvärinen, A.
Artificial Neural Networks and Machine Learning – ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I. ed. / T Honkela. Berlin, Heidelberg: Springer, 2011. p. 323-330 (Lecture Notes in Computer Science; Vol. 6791).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Extracting coactivated features from multiple data sets

AU - Gutmann, M.

AU - Hyvärinen, A.

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-21735-7_40

DO - 10.1007/978-3-642-21735-7_40

M3 - Conference contribution

SN - 978-3-642-21734-0

T3 - Lecture Notes in Computer Science

SP - 323

EP - 330

BT - Artificial Neural Networks and Machine Learning – ICANN 2011

A2 - Honkela, T

PB - Springer

CY - Berlin, Heidelberg

ER -

Gutmann M, Hyvärinen A. Extracting coactivated features from multiple data sets. In Honkela T, editor, Artificial Neural Networks and Machine Learning – ICANN 2011: 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I. Berlin, Heidelberg: Springer. 2011. p. 323-330. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-21735-7_40

Extracting coactivated features from multiple data sets

Abstract

Publication series

Access to Document

Fingerprint

Cite this