國立虎尾科技大學 |

Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics = = Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics =/
Reminder of title:	Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
remainder title:	Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
Author:	Bonneville, Christophe.
Description:	1 online resource (180 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
Subject:	Computational physics. -
Online resource:	click for full text (PQDT)
ISBN:	9798379711559

Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics = = Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
Bonneville, Christophe.

Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics =Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique. - 1 online resource (180 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--Cornell University, 2023.

Includes bibliographical references

Bayesian machine learning methods are capable of making predictions with well-quantified uncertainty, and tend to be inherently more robust to noisy data. This makes such methods particularly interesting in engineering and scientific problems that require the use of interpretable machine learning algorithms, but where the available data is sparse and noisy. In this thesis, we explore and demonstrate the usefulness of Bayesian machine learning algorithms in several categories of computational engineering problems. First, we present two Gaussian process-based algorithms for failure prediction of structural components. Second, we show how Bayesian optimization can be applied to efficiently optimize engineering designs that require to be validated by time consuming forward simulations, such as fluid-structure interaction simulations. Third, we demonstrate how Bayesian neural networks can be used for scientific discovery, and present a method to discover unknown partial differential equations from sparse data. Finally, we present a Gaussian process-based reduced-order-model capable of efficiently collecting training data, with application to fluid dynamics simulations.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798379711559Subjects--Topical Terms:

1181955
Computational physics.
Subjects--Index Terms:

Bayesian methodsIndex Terms--Genre/Form:

554714
Electronic books.

Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics = = Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
LDR:04478ntm a22004337 4500 001 1146602
005 20240812064654.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379711559
035 $a (MiAaPQ)AAI30425214
035 $a AAI30425214
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Bonneville, Christophe. $3 1472015
245 1 0 $a Bayesian Machine Learning Algorithms for Uncertainty Quantification, Optimization, and Equation Discoveries in Engineering Physics = $b Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
246 3 1 $a Algorithmes de machine learning bayesiens pour la quantification d'incertitude, l'optimisation et la decouverte d'equations en physique et genie mecanique.
264 0 $c 2023
300 $a 1 online resource (180 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
500 $a Advisor: Earls, Christopher.
502 $a Thesis (Ph.D.)--Cornell University, 2023.
504 $a Includes bibliographical references
520 $a Bayesian machine learning methods are capable of making predictions with well-quantified uncertainty, and tend to be inherently more robust to noisy data. This makes such methods particularly interesting in engineering and scientific problems that require the use of interpretable machine learning algorithms, but where the available data is sparse and noisy. In this thesis, we explore and demonstrate the usefulness of Bayesian machine learning algorithms in several categories of computational engineering problems. First, we present two Gaussian process-based algorithms for failure prediction of structural components. Second, we show how Bayesian optimization can be applied to efficiently optimize engineering designs that require to be validated by time consuming forward simulations, such as fluid-structure interaction simulations. Third, we demonstrate how Bayesian neural networks can be used for scientific discovery, and present a method to discover unknown partial differential equations from sparse data. Finally, we present a Gaussian process-based reduced-order-model capable of efficiently collecting training data, with application to fluid dynamics simulations.
520 $a Les methodes de machine learning (apprentissage automatique) bayesiennes sont capables de faire des predictions avec une incertitude bien quantifiee et ont tendance a etre intrinsequement plus robustes aux donnees corrompues. Cela rend ces methodes particulierement interessantes pour les problemes scientifiques et d'ingenierie qui necessitent l'utilisation d'algorithmes d'apprentissage automatique interpretables, mais dont les donnees disponibles sont rares et corrompues. Dans cette these, nous explorons et demontrons l'utilite des algorithmes d'apprentissage automatique bayesiens dans plusieurs categories de problemes d'ingenierie numerique. Tout d'abord, nous presentons deux algorithmes bases sur des processus gaussiens pour predire la defaillance de composants structuraux. Deuxiemement, nous montrons comment l'optimisation bayesienne peut etre utilisee pour optimiser efficacement des designs qui necessitent d'etre validees par des simulations couteuses, telles que les simulations d'interaction fluide-structure. Troisiemement, nous demontrons comment des reseaux de neurones bayesiens peuvent etre utilises pour la decouverte scientifique et presentons une methode pour decouvrir des equations aux derivees partielles inconnues a partir de donnees limitees. Enfin, nous presentons un modele d'ordre reduit base sur des processus gaussiens capable de collecter efficacement des donnees d'entrainement, avec une application aux simulations de dynamique des fluides.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computational physics. $3 1181955
650 4 $a Mechanical engineering. $3 557493
650 4 $a Applied mathematics. $3 1069907
653 $a Bayesian methods
653 $a Gaussian process
653 $a Machine learning
653 $a Numerical simulation
653 $a Partial differential equations
655 7 $a Electronic books. $2 local $3 554714
690 $a 0216
690 $a 0800
690 $a 0548
690 $a 0364
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Cornell University. $b Civil and Environmental Engineering. $3 1182991
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30425214 $z click for full text (PQDT)