A Bayesian multiple kernel learning framework for single and multiple output regression

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on classification formulations and there are few attempts for regression. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation for single output regression. We then show that the proposed formulation can be extended to multiple output regression. We illustrate the effectiveness of our approach on a single output benchmark data set. Our framework outperforms previously reported results with better generalization performance on two image recognition data sets using both single and multiple output formulations.

Original languageEnglish (US)
Title of host publicationFrontiers in Artificial Intelligence and Applications
PublisherIOS Press
Pages354-359
Number of pages6
Volume242
ISBN (Print)9781614990970
DOIs
StatePublished - 2012
Externally publishedYes

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume242
ISSN (Print)09226389

Fingerprint

Image recognition
Learning algorithms

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Gonen, M. (2012). A Bayesian multiple kernel learning framework for single and multiple output regression. In Frontiers in Artificial Intelligence and Applications (Vol. 242, pp. 354-359). (Frontiers in Artificial Intelligence and Applications; Vol. 242). IOS Press. https://doi.org/10.3233/978-1-61499-098-7-354

A Bayesian multiple kernel learning framework for single and multiple output regression. / Gonen, Mehmet.

Frontiers in Artificial Intelligence and Applications. Vol. 242 IOS Press, 2012. p. 354-359 (Frontiers in Artificial Intelligence and Applications; Vol. 242).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gonen, M 2012, A Bayesian multiple kernel learning framework for single and multiple output regression. in Frontiers in Artificial Intelligence and Applications. vol. 242, Frontiers in Artificial Intelligence and Applications, vol. 242, IOS Press, pp. 354-359. https://doi.org/10.3233/978-1-61499-098-7-354
Gonen M. A Bayesian multiple kernel learning framework for single and multiple output regression. In Frontiers in Artificial Intelligence and Applications. Vol. 242. IOS Press. 2012. p. 354-359. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-098-7-354
Gonen, Mehmet. / A Bayesian multiple kernel learning framework for single and multiple output regression. Frontiers in Artificial Intelligence and Applications. Vol. 242 IOS Press, 2012. pp. 354-359 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{44b9d0fe795341a280443bc6a076216a,
title = "A Bayesian multiple kernel learning framework for single and multiple output regression",
abstract = "Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on classification formulations and there are few attempts for regression. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation for single output regression. We then show that the proposed formulation can be extended to multiple output regression. We illustrate the effectiveness of our approach on a single output benchmark data set. Our framework outperforms previously reported results with better generalization performance on two image recognition data sets using both single and multiple output formulations.",
author = "Mehmet Gonen",
year = "2012",
doi = "10.3233/978-1-61499-098-7-354",
language = "English (US)",
isbn = "9781614990970",
volume = "242",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "354--359",
booktitle = "Frontiers in Artificial Intelligence and Applications",

}

TY - GEN

T1 - A Bayesian multiple kernel learning framework for single and multiple output regression

AU - Gonen, Mehmet

PY - 2012

Y1 - 2012

N2 - Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on classification formulations and there are few attempts for regression. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation for single output regression. We then show that the proposed formulation can be extended to multiple output regression. We illustrate the effectiveness of our approach on a single output benchmark data set. Our framework outperforms previously reported results with better generalization performance on two image recognition data sets using both single and multiple output formulations.

AB - Multiple kernel learning algorithms are proposed to combine kernels in order to obtain a better similarity measure or to integrate feature representations coming from different data sources. Most of the previous research on such methods is focused on classification formulations and there are few attempts for regression. We propose a fully conjugate Bayesian formulation and derive a deterministic variational approximation for single output regression. We then show that the proposed formulation can be extended to multiple output regression. We illustrate the effectiveness of our approach on a single output benchmark data set. Our framework outperforms previously reported results with better generalization performance on two image recognition data sets using both single and multiple output formulations.

UR - http://www.scopus.com/inward/record.url?scp=84878772181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878772181&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-098-7-354

DO - 10.3233/978-1-61499-098-7-354

M3 - Conference contribution

AN - SCOPUS:84878772181

SN - 9781614990970

VL - 242

T3 - Frontiers in Artificial Intelligence and Applications

SP - 354

EP - 359

BT - Frontiers in Artificial Intelligence and Applications

PB - IOS Press

ER -