Universum learning for SVM regression

Sauptik Dhar; Vladimir Cherkassky

doi:10.1109/IJCNN.2017.7966314

Universum learning for SVM regression

Sauptik Dhar, Vladimir Cherkassky

Electrical and Computer Engineering

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

2 Scopus citations

Abstract

This paper extends the idea of Universum learning to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples, or Universum samples, belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons are presented to illustrate the utility of the proposed approach.

Original language	English (US)
Title of host publication	2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3641-3648
Number of pages	8
ISBN (Electronic)	9781509061815
DOIs	https://doi.org/10.1109/IJCNN.2017.7966314
State	Published - Jun 30 2017
Event	2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States Duration: May 14 2017 → May 19 2017

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2017-May

Other

Other	2017 International Joint Conference on Neural Networks, IJCNN 2017
Country/Territory	United States
City	Anchorage
Period	5/14/17 → 5/19/17

Bibliographical note

Funding Information:
Acknowledgement: The work of V. Cherkassky was supported, in part, by NIH grant U01NS073557 and by NIH grant R01NS092882.

Publisher Copyright:
© 2017 IEEE.

Keywords

Learning through contradiction
Support Vector Regression
Universum Learning

Publisher link

10.1109/IJCNN.2017.7966314

Find It

Find It at U of M Libraries

Cite this

Dhar, S., & Cherkassky, V. (2017). Universum learning for SVM regression. In 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings (pp. 3641-3648). [7966314] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2017.7966314

Universum learning for SVM regression. / Dhar, Sauptik; Cherkassky, Vladimir.
2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 3641-3648 7966314 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017-May).

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

Dhar, S & Cherkassky, V 2017, Universum learning for SVM regression. in 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings., 7966314, Proceedings of the International Joint Conference on Neural Networks, vol. 2017-May, Institute of Electrical and Electronics Engineers Inc., pp. 3641-3648, 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, United States, 5/14/17. https://doi.org/10.1109/IJCNN.2017.7966314

@inproceedings{0503e38e08e94f8aa534a277601c916c,

title = "Universum learning for SVM regression",

abstract = "This paper extends the idea of Universum learning to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples, or Universum samples, belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons are presented to illustrate the utility of the proposed approach.",

keywords = "Learning through contradiction, Support Vector Regression, Universum Learning",

author = "Sauptik Dhar and Vladimir Cherkassky",

note = "Funding Information: Acknowledgement: The work of V. Cherkassky was supported, in part, by NIH grant U01NS073557 and by NIH grant R01NS092882. Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 International Joint Conference on Neural Networks, IJCNN 2017 ; Conference date: 14-05-2017 Through 19-05-2017",

year = "2017",

month = jun,

day = "30",

doi = "10.1109/IJCNN.2017.7966314",

language = "English (US)",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3641--3648",

booktitle = "2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings",

}

TY - GEN

T1 - Universum learning for SVM regression

AU - Dhar, Sauptik

AU - Cherkassky, Vladimir

PY - 2017/6/30

Y1 - 2017/6/30

N2 - This paper extends the idea of Universum learning to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples, or Universum samples, belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons are presented to illustrate the utility of the proposed approach.

AB - This paper extends the idea of Universum learning to regression problems. We propose new Universum-SVM formulation for regression problems that incorporates a priori knowledge in the form of additional data samples. These additional data samples, or Universum samples, belong to the same application domain as the training samples, but they follow a different distribution. Several empirical comparisons are presented to illustrate the utility of the proposed approach.

KW - Learning through contradiction

KW - Support Vector Regression

KW - Universum Learning

UR - http://www.scopus.com/inward/record.url?scp=85030994874&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030994874&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2017.7966314

DO - 10.1109/IJCNN.2017.7966314

M3 - Conference contribution

AN - SCOPUS:85030994874

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3641

EP - 3648

BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017

Y2 - 14 May 2017 through 19 May 2017

ER -

Universum learning for SVM regression

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Cite this