본문

서브메뉴

Advances in Intuitive Priors and Scalable Algorithms for Bayesian Deep Neural Network Models in Scientific Applications
Advances in Intuitive Priors and Scalable Algorithms for Bayesian Deep Neural Network Mode...
Advances in Intuitive Priors and Scalable Algorithms for Bayesian Deep Neural Network Models in Scientific Applications

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152055
ISBN  
9798382739007
DDC  
510
저자명  
Hauth, Jeremiah M. A.
서명/저자  
Advances in Intuitive Priors and Scalable Algorithms for Bayesian Deep Neural Network Models in Scientific Applications
발행사항  
[Sl] : University of Michigan, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
145 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Huan, Xun.
학위논문주기  
Thesis (Ph.D.)--University of Michigan, 2024.
초록/해제  
요약In recent years, deep learning (DL) algorithms have gained widespread use in scientific and engineering fields, promising insights into complex trends within extensive datasets. However, these models typically lack transparency and interpretability and the quantification of uncertainty in DL models, especially related to the understanding derived from the quality and quantity of training data, remains an underexplored research area. This dissertation addresses this gap by advancing Bayesian uncertainty quantification (UQ) methods in large-scale deep neural networks (DNNs), specifically constructing Bayesian neural networks (BNNs). This dissertation proposes two methodological improvements to BNNs: the first is a parameter subselection procedure that leverages gradient based sensitivity analysis to select only the most impactful DL parameters for Bayesian inference; the second contribution is a prior selection methodology that weighs both expert knowledge of the predictive space alongside as well as desirable regularizing effects in the weight space. This dissertation goes on to implement Bayesian neural networks and these novel methodologies in four unique scientific machine learning case studies, two related to physics simulations and two related to real-world health data. These case studies include: a novel framework for remotely detecting ice accumulation on helicopter rotor blades and assessing flight performance degradation; an investigation on the temporal evolution of uncertainty in Bayesian graph convolutional neural networks when predicting stress response in polycrystalline materials; an investigation of the uncertainty in the state-of-the-art U-NET model for brain tumor segmentation; and a novel framework for automatically assessing physical therapy patient performance on balance training exercises, along with preliminary approaches for future exercise recommendation. By drawing new insights into model uncertainty across diverse science and engineering applications, this research aims to provide greater understanding of uncertainty in Bayesian neural networks, to help mitigate the consequences of model overconfidence, and to provide critical metrics for decision-making and data collection.
일반주제명  
Mathematics
일반주제명  
Mechanical engineering
키워드  
Uncertainty quantification
키워드  
Bayesian neural networks
키워드  
Scientific machine learning
키워드  
Scalable Bayesian inference
키워드  
Deep neural networks
기타저자  
University of Michigan Mechanical Engineering
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162793
■00520250211152055
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382739007
■035    ▼a(MiAaPQ)AAI31348909
■035    ▼a(MiAaPQ)umichrackham005424
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a510
■1001  ▼aHauth,  Jeremiah  M.  A.
■24510▼aAdvances  in  Intuitive  Priors  and  Scalable  Algorithms  for  Bayesian  Deep  Neural  Network  Models  in  Scientific  Applications
■260    ▼a[Sl]▼bUniversity  of  Michigan▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a145  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Huan,  Xun.
■5021  ▼aThesis  (Ph.D.)--University  of  Michigan,  2024.
■520    ▼aIn  recent  years,  deep  learning  (DL)  algorithms  have  gained  widespread  use  in  scientific  and  engineering  fields,  promising  insights  into  complex  trends  within  extensive  datasets.  However,  these  models  typically  lack  transparency  and  interpretability  and  the  quantification  of  uncertainty  in  DL  models,  especially  related  to  the  understanding  derived  from  the  quality  and  quantity  of  training  data,  remains  an  underexplored  research  area.  This  dissertation  addresses  this  gap  by  advancing  Bayesian  uncertainty  quantification  (UQ)  methods  in  large-scale  deep  neural  networks  (DNNs),  specifically  constructing  Bayesian  neural  networks  (BNNs).    This  dissertation  proposes  two  methodological  improvements  to  BNNs:  the  first  is  a  parameter  subselection  procedure  that  leverages  gradient  based  sensitivity  analysis  to  select  only  the  most  impactful  DL  parameters  for  Bayesian  inference;  the  second  contribution  is  a  prior  selection  methodology  that  weighs  both  expert  knowledge  of  the  predictive  space  alongside  as  well  as  desirable  regularizing  effects  in  the  weight  space.    This  dissertation  goes  on  to  implement  Bayesian  neural  networks  and  these  novel  methodologies  in  four  unique  scientific  machine  learning  case  studies,  two  related  to  physics  simulations  and  two  related  to  real-world  health  data.  These  case  studies  include:  a  novel  framework  for  remotely  detecting  ice  accumulation  on  helicopter  rotor  blades  and  assessing  flight  performance  degradation;  an  investigation  on  the  temporal  evolution  of  uncertainty  in  Bayesian  graph  convolutional  neural  networks  when  predicting  stress  response  in  polycrystalline  materials;  an  investigation  of  the  uncertainty  in  the  state-of-the-art  U-NET  model  for  brain  tumor  segmentation;  and  a  novel  framework  for  automatically  assessing  physical  therapy  patient  performance  on  balance  training  exercises,  along  with  preliminary  approaches  for  future  exercise  recommendation.    By  drawing  new  insights  into  model  uncertainty  across  diverse  science  and  engineering  applications,  this  research  aims  to  provide  greater  understanding  of  uncertainty  in  Bayesian  neural  networks,  to  help  mitigate  the  consequences  of  model  overconfidence,  and  to  provide  critical  metrics  for  decision-making  and  data  collection.
■590    ▼aSchool  code:  0127.
■650  4▼aMathematics
■650  4▼aMechanical  engineering
■653    ▼aUncertainty  quantification
■653    ▼aBayesian  neural  networks
■653    ▼aScientific  machine  learning
■653    ▼aScalable  Bayesian  inference
■653    ▼aDeep  neural  networks
■690    ▼a0548
■690    ▼a0405
■690    ▼a0800
■71020▼aUniversity  of  Michigan▼bMechanical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0127
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162793▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF10347 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.