Skip to main content

A Bayesian approach to joint feature selection and classifier design.

Publication ,  Journal Article
Krishnapuram, B; Hartemink, AJ; Carin, L; Figueiredo, MAT
Published in: IEEE transactions on pattern analysis and machine intelligence
September 2004

This paper adopts a Bayesian approach to simultaneously learn both an optimal nonlinear classifier and a subset of predictor variables (or features) that are most relevant to the classification task. The approach uses heavy-tailed priors to promote sparsity in the utilization of both basis functions and features; these priors act as regularizers for the likelihood function that rewards good classification on the training data. We derive an expectation-maximization (EM) algorithm to efficiently compute a maximum a posteriori (MAP) point estimate of the various parameters. The algorithm is an extension of recent state-of-the-art sparse Bayesian classifiers, which in turn can be seen as Bayesian counterparts of support vector machines. Experimental comparisons using kernel classifiers demonstrate both parsimonious feature selection and excellent classification accuracy on a range of synthetic and benchmark data sets.

Duke Scholars

Published In

IEEE transactions on pattern analysis and machine intelligence

DOI

EISSN

1939-3539

ISSN

0162-8828

Publication Date

September 2004

Volume

26

Issue

9

Start / End Page

1105 / 1111

Related Subject Headings

  • Sensitivity and Specificity
  • Reproducibility of Results
  • Pattern Recognition, Automated
  • Models, Statistical
  • Models, Biological
  • Leukemia
  • Information Storage and Retrieval
  • Humans
  • Gene Expression Profiling
  • Diagnosis, Computer-Assisted
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Krishnapuram, B., Hartemink, A. J., Carin, L., & Figueiredo, M. A. T. (2004). A Bayesian approach to joint feature selection and classifier design. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(9), 1105–1111. https://doi.org/10.1109/tpami.2004.55
Krishnapuram, Balaji, Alexander J. Hartemink, Lawrence Carin, and Mário A. T. Figueiredo. “A Bayesian approach to joint feature selection and classifier design.IEEE Transactions on Pattern Analysis and Machine Intelligence 26, no. 9 (September 2004): 1105–11. https://doi.org/10.1109/tpami.2004.55.
Krishnapuram B, Hartemink AJ, Carin L, Figueiredo MAT. A Bayesian approach to joint feature selection and classifier design. IEEE transactions on pattern analysis and machine intelligence. 2004 Sep;26(9):1105–11.
Krishnapuram, Balaji, et al. “A Bayesian approach to joint feature selection and classifier design.IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 9, Sept. 2004, pp. 1105–11. Epmc, doi:10.1109/tpami.2004.55.
Krishnapuram B, Hartemink AJ, Carin L, Figueiredo MAT. A Bayesian approach to joint feature selection and classifier design. IEEE transactions on pattern analysis and machine intelligence. 2004 Sep;26(9):1105–1111.

Published In

IEEE transactions on pattern analysis and machine intelligence

DOI

EISSN

1939-3539

ISSN

0162-8828

Publication Date

September 2004

Volume

26

Issue

9

Start / End Page

1105 / 1111

Related Subject Headings

  • Sensitivity and Specificity
  • Reproducibility of Results
  • Pattern Recognition, Automated
  • Models, Statistical
  • Models, Biological
  • Leukemia
  • Information Storage and Retrieval
  • Humans
  • Gene Expression Profiling
  • Diagnosis, Computer-Assisted