Multi-objective optimization of support vector machines

Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review

Standard

Multi-objective optimization of support vector machines. / Suttorp, Thorsten; Igel, Christian.

Multi-objective machine learning. ed. / Yaochu Jin. Springer, 2006. p. 199-220 (Studies in Computational Intelligence, Vol. 16).

Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review

Harvard

Suttorp, T & Igel, C 2006, Multi-objective optimization of support vector machines. in Y Jin (ed.), Multi-objective machine learning. Springer, Studies in Computational Intelligence, vol. 16, pp. 199-220. https://doi.org/10.1007/11399346_9

APA

Suttorp, T., & Igel, C. (2006). Multi-objective optimization of support vector machines. In Y. Jin (Ed.), Multi-objective machine learning (pp. 199-220). Springer. Studies in Computational Intelligence Vol. 16 https://doi.org/10.1007/11399346_9

Vancouver

Suttorp T, Igel C. Multi-objective optimization of support vector machines. In Jin Y, editor, Multi-objective machine learning. Springer. 2006. p. 199-220. (Studies in Computational Intelligence, Vol. 16). https://doi.org/10.1007/11399346_9

Author

Suttorp, Thorsten ; Igel, Christian. / Multi-objective optimization of support vector machines. Multi-objective machine learning. editor / Yaochu Jin. Springer, 2006. pp. 199-220 (Studies in Computational Intelligence, Vol. 16).

Bibtex

@inbook{43a3b93de7b143ce84f503447714d2fe,
title = "Multi-objective optimization of support vector machines",
abstract = "Designing supervised learning systems is in general a multi-objective optimization problem. It requires finding appropriate trade-offs between several objectives, for example between model complexity and accuracy or sensitivity and specificity. We consider the adaptation of kernel and regularization parameters of support vector machines (SVMs) by means of multi-objective evolutionary optimization. Support vector machines are reviewed from the multi-objective perspective, and different encodings and model selection criteria are described. The optimization of split modified radius-margin model selection criteria is demonstrated on benchmark problems. The MOO approach to SVM design is evaluated on a real-world pattern recognition task, namely the real-time detection of pedestrians in infrared images for driver assistance systems. Here the three objectives are the minimization of the false positive rate, the false negative rate, and the number of support vectors to reduce the computational complexity.",
author = "Thorsten Suttorp and Christian Igel",
year = "2006",
doi = "10.1007/11399346_9",
language = "English",
isbn = "978-3-540-30676-4",
series = "Studies in Computational Intelligence",
publisher = "Springer",
pages = "199--220",
editor = "Yaochu Jin",
booktitle = "Multi-objective machine learning",
address = "Switzerland",

}

RIS

TY - CHAP

T1 - Multi-objective optimization of support vector machines

AU - Suttorp, Thorsten

AU - Igel, Christian

PY - 2006

Y1 - 2006

N2 - Designing supervised learning systems is in general a multi-objective optimization problem. It requires finding appropriate trade-offs between several objectives, for example between model complexity and accuracy or sensitivity and specificity. We consider the adaptation of kernel and regularization parameters of support vector machines (SVMs) by means of multi-objective evolutionary optimization. Support vector machines are reviewed from the multi-objective perspective, and different encodings and model selection criteria are described. The optimization of split modified radius-margin model selection criteria is demonstrated on benchmark problems. The MOO approach to SVM design is evaluated on a real-world pattern recognition task, namely the real-time detection of pedestrians in infrared images for driver assistance systems. Here the three objectives are the minimization of the false positive rate, the false negative rate, and the number of support vectors to reduce the computational complexity.

AB - Designing supervised learning systems is in general a multi-objective optimization problem. It requires finding appropriate trade-offs between several objectives, for example between model complexity and accuracy or sensitivity and specificity. We consider the adaptation of kernel and regularization parameters of support vector machines (SVMs) by means of multi-objective evolutionary optimization. Support vector machines are reviewed from the multi-objective perspective, and different encodings and model selection criteria are described. The optimization of split modified radius-margin model selection criteria is demonstrated on benchmark problems. The MOO approach to SVM design is evaluated on a real-world pattern recognition task, namely the real-time detection of pedestrians in infrared images for driver assistance systems. Here the three objectives are the minimization of the false positive rate, the false negative rate, and the number of support vectors to reduce the computational complexity.

U2 - 10.1007/11399346_9

DO - 10.1007/11399346_9

M3 - Book chapter

AN - SCOPUS:33845346175

SN - 978-3-540-30676-4

T3 - Studies in Computational Intelligence

SP - 199

EP - 220

BT - Multi-objective machine learning

A2 - Jin, Yaochu

PB - Springer

ER -

ID: 168323865