Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters

This paper deals with the application of the support vector machine (SVM) and the least-squares SVM regressions to the uncertainty quantification of complex systems with a high-dimensional parameter space. The above regression techniques are used to build accurate and compact surrogate models of the...

Full description

Bibliographic Details
Main Authors:	Riccardo Trinchero, Mourad Larbi, Hakki M. Torun, Flavio G. Canavero, Madhavan Swaminathan
Format:	Article
Language:	English
Published:	IEEE 2019-01-01
Series:	IEEE Access
Subjects:	Machine learning uncertainty quantification parameterized modeling surrogate models SVM regression LS-SVM regression
Online Access:	https://ieeexplore.ieee.org/document/8584446/

id	doaj-b77e3fefedc14c6f95d36b78c8a6cf56
record_format	Article
spelling	doaj-b77e3fefedc14c6f95d36b78c8a6cf562021-03-29T22:11:34ZengIEEEIEEE Access2169-35362019-01-0174056406610.1109/ACCESS.2018.28889038584446Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of ParametersRiccardo Trinchero0https://orcid.org/0000-0002-1838-2591Mourad Larbi1Hakki M. Torun2Flavio G. Canavero3Madhavan Swaminathan4Department of Electronics and Telecommunications, Politecnico di Torino, Turin, ItalySchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USASchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USADepartment of Electronics and Telecommunications, Politecnico di Torino, Turin, ItalySchool of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USAThis paper deals with the application of the support vector machine (SVM) and the least-squares SVM regressions to the uncertainty quantification of complex systems with a high-dimensional parameter space. The above regression techniques are used to build accurate and compact surrogate models of the system responses from a limited set of training samples. The accuracy and the feasibility of the proposed modeling techniques are then investigated by comparing their results with the ones predicted by a sparse polynomial chaos expansion by considering two real-life problems with 8 and 30 random variables, respectively.https://ieeexplore.ieee.org/document/8584446/Machine learninguncertainty quantificationparameterized modelingsurrogate modelsSVM regressionLS-SVM regression
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Riccardo Trinchero Mourad Larbi Hakki M. Torun Flavio G. Canavero Madhavan Swaminathan
spellingShingle	Riccardo Trinchero Mourad Larbi Hakki M. Torun Flavio G. Canavero Madhavan Swaminathan Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters IEEE Access Machine learning uncertainty quantification parameterized modeling surrogate models SVM regression LS-SVM regression
author_facet	Riccardo Trinchero Mourad Larbi Hakki M. Torun Flavio G. Canavero Madhavan Swaminathan
author_sort	Riccardo Trinchero
title	Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters
title_short	Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters
title_full	Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters
title_fullStr	Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters
title_full_unstemmed	Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters
title_sort	machine learning and uncertainty quantification for surrogate models of integrated devices with a large number of parameters
publisher	IEEE
series	IEEE Access
issn	2169-3536
publishDate	2019-01-01
description	This paper deals with the application of the support vector machine (SVM) and the least-squares SVM regressions to the uncertainty quantification of complex systems with a high-dimensional parameter space. The above regression techniques are used to build accurate and compact surrogate models of the system responses from a limited set of training samples. The accuracy and the feasibility of the proposed modeling techniques are then investigated by comparing their results with the ones predicted by a sparse polynomial chaos expansion by considering two real-life problems with 8 and 30 random variables, respectively.
topic	Machine learning uncertainty quantification parameterized modeling surrogate models SVM regression LS-SVM regression
url	https://ieeexplore.ieee.org/document/8584446/
work_keys_str_mv	AT riccardotrinchero machinelearninganduncertaintyquantificationforsurrogatemodelsofintegrateddeviceswithalargenumberofparameters AT mouradlarbi machinelearninganduncertaintyquantificationforsurrogatemodelsofintegrateddeviceswithalargenumberofparameters AT hakkimtorun machinelearninganduncertaintyquantificationforsurrogatemodelsofintegrateddeviceswithalargenumberofparameters AT flaviogcanavero machinelearninganduncertaintyquantificationforsurrogatemodelsofintegrateddeviceswithalargenumberofparameters AT madhavanswaminathan machinelearninganduncertaintyquantificationforsurrogatemodelsofintegrateddeviceswithalargenumberofparameters
_version_	1724192095242027008

Machine Learning and Uncertainty Quantification for Surrogate Models of Integrated Devices With a Large Number of Parameters

Similar Items