Advanced search
2 files | 733.12 KB Add to list

A surrogate modeling and adaptive sampling toolbox for computer based design

Dirk Gorissen (UGent) , Ivo Couckuyt (UGent) , Piet Demeester (UGent) , Tom Dhaene (UGent) and Karel Crombecq
Author
Organization
Abstract
An exceedingly large number of scientific and engineering fields are confronted with the need for computer simulations to study complex, real world phenomena or solve challenging design problems. However, due to the computational cost of these high fidelity simulations, the use of neural networks, kernel methods, and other surrogate modeling techniques have become indispensable. Surrogate models are compact and cheap to evaluate, and have proven very useful for tasks such as optimization, design space exploration, prototyping, and sensitivity analysis. Consequently, in many fields there is great interest in tools and techniques that facilitate the construction of such regression models, while minimizing the computational cost and maximizing model accuracy. This paper presents a mature, flexible, and adaptive machine learning toolkit for regression modeling and active learning to tackle these issues. The toolkit brings together algorithms for data fitting, model selection, sample selection (active learning), hyperparameter optimization, and distributed computing in order to empower a domain expert to efficiently generate an accurate model for the problem or data at hand.
Keywords
metamodeling, surrogate modeling, function approximation, model selection, adaptive sampling, active learning, distributed computing

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 324.42 KB
  • 4407 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 408.70 KB

Citation

Please use this url to cite or link to this publication:

MLA
Gorissen, Dirk et al. “A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design.” JOURNAL OF MACHINE LEARNING RESEARCH 11 (2010): 2051–2055. Print.
APA
Gorissen, D., Couckuyt, I., Demeester, P., Dhaene, T., & Crombecq, K. (2010). A surrogate modeling and adaptive sampling toolbox for computer based design. JOURNAL OF MACHINE LEARNING RESEARCH, 11, 2051–2055.
Chicago author-date
Gorissen, Dirk, Ivo Couckuyt, Piet Demeester, Tom Dhaene, and Karel Crombecq. 2010. “A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design.” Journal of Machine Learning Research 11: 2051–2055.
Chicago author-date (all authors)
Gorissen, Dirk, Ivo Couckuyt, Piet Demeester, Tom Dhaene, and Karel Crombecq. 2010. “A Surrogate Modeling and Adaptive Sampling Toolbox for Computer Based Design.” Journal of Machine Learning Research 11: 2051–2055.
Vancouver
1.
Gorissen D, Couckuyt I, Demeester P, Dhaene T, Crombecq K. A surrogate modeling and adaptive sampling toolbox for computer based design. JOURNAL OF MACHINE LEARNING RESEARCH. 2010;11:2051–5.
IEEE
[1]
D. Gorissen, I. Couckuyt, P. Demeester, T. Dhaene, and K. Crombecq, “A surrogate modeling and adaptive sampling toolbox for computer based design,” JOURNAL OF MACHINE LEARNING RESEARCH, vol. 11, pp. 2051–2055, 2010.
@article{1140837,
  abstract     = {{An exceedingly large number of scientific and engineering fields are confronted with the need for computer simulations to study complex, real world phenomena or solve challenging design problems. However, due to the computational cost of these high fidelity simulations, the use of neural networks, kernel methods, and other surrogate modeling techniques have become indispensable. Surrogate models are compact and cheap to evaluate, and have proven very useful for tasks such as optimization, design space exploration, prototyping, and sensitivity analysis. Consequently, in many fields there is great interest in tools and techniques that facilitate the construction of such regression models, while minimizing the computational cost and maximizing model accuracy. This paper presents a mature, flexible, and adaptive machine learning toolkit for regression modeling and active learning to tackle these issues. The toolkit brings together algorithms for data fitting, model selection, sample selection (active learning), hyperparameter optimization, and distributed computing in order to empower a domain expert to efficiently generate an accurate model for the problem or data at hand.}},
  author       = {{Gorissen, Dirk and Couckuyt, Ivo and Demeester, Piet and Dhaene, Tom and Crombecq, Karel}},
  issn         = {{1532-4435}},
  journal      = {{JOURNAL OF MACHINE LEARNING RESEARCH}},
  keywords     = {{metamodeling,surrogate modeling,function approximation,model selection,adaptive sampling,active learning,distributed computing}},
  language     = {{eng}},
  pages        = {{2051--2055}},
  title        = {{A surrogate modeling and adaptive sampling toolbox for computer based design}},
  url          = {{http://www.sumo.intec.ugent.be/files/2010_07_JMLR.pdf}},
  volume       = {{11}},
  year         = {{2010}},
}

Web of Science
Times cited: