본문

서브메뉴

Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211153108
ISBN  
9798346392620
DDC  
515.35
저자명  
Nasim, Md.
서명/저자  
Accelerating Ai-Driven Scientific Discovery With End-To-End Learning and Random Projection
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
117 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
주기사항  
Advisor: Xue, Yexiang.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약Scientific discovery of new knowledge from data can enhance our understanding of the physical world and lead to the innovation of new technologies. AI-driven methods can greatly accelerate scientific discovery and are essential for analyzing and identifying patterns in huge volumes of experimental data. However, current AI-driven scientific discovery pipeline suffers from several inefficiencies including but not limited to lack of precise modeling, lack of efficient learning methods, and lack of human-in-the-loop integrated frameworksin the scientific discovery loop. Such inefficiencies increase resource requirements such as expensive computing infrastructures, significant human expert efforts and subsequently slows down scientific discovery.In this thesis, I introduce a collection of methods to address the lack of precise modeling, lack of efficient learning methods and lack of human-in-the-loop integrated frameworks in AI-driven scientific discovery workflow. These methods include automatic physics model learning from partially annotated noisy video data, accelerated partial differential equation (PDE) physics model learning, and an integrated AI-driven platform for rapid analysis of experimental video data. My research has led to the discovery of a new size fluctuation property of material defectsexposed to high temperature and high irradiation environments such as inside nuclear reactors. Such discovery is essential for designing strong materials that are critical for energy applications.To address the lack of precise modeling of physics learning tasks, I developed NeuraDiff [1], an end-to-end method for learning phase field physics models from noisy video data. In previous learning approaches involving multiple disjoint steps, errors in one step can propagate to another, thus affecting the accuracy of the learned physics models. Trial-and-error simulation methods for learning physics model parameters are inefficient, heavily dependent on expert intuition and may not yield reasonably accurate physics models even after many trial iterations. By encoding the physics model equations directly into learning, end-to-end NeuraDiff framework can provide ≈ 100% accurate tracking of material defects and yield correct physics model parameters.
일반주제명  
Partial differential equations
일반주제명  
Deep learning
일반주제명  
Defects
일반주제명  
Back propagation
일반주제명  
Fourier transforms
일반주제명  
Grain growth
일반주제명  
High temperature
일반주제명  
Neural networks
일반주제명  
Microscopy
일반주제명  
Heat
일반주제명  
Crowdsourcing
일반주제명  
Human error
일반주제명  
Radiation
일반주제명  
Data compression
일반주제명  
Computer science
일반주제명  
High temperature physics
일반주제명  
Mathematics
일반주제명  
Thermodynamics
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164966
■00520250211153108
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346392620
■035    ▼a(MiAaPQ)AAI31682051
■035    ▼a(MiAaPQ)Purdue26815507
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a515.35
■1001  ▼aNasim,  Md.
■24510▼aAccelerating  Ai-Driven  Scientific  Discovery  With  End-To-End  Learning  and  Random  Projection
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a117  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  B.
■500    ▼aAdvisor:  Xue,  Yexiang.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼aScientific  discovery  of  new  knowledge  from  data  can  enhance  our  understanding  of  the  physical  world  and  lead  to  the  innovation  of  new  technologies.  AI-driven  methods  can  greatly  accelerate  scientific  discovery  and  are  essential  for  analyzing  and  identifying  patterns  in  huge  volumes  of  experimental  data.  However,  current  AI-driven  scientific  discovery  pipeline  suffers  from  several  inefficiencies  including  but  not  limited  to  lack  of  precise  modeling,  lack  of  efficient  learning  methods,  and  lack  of  human-in-the-loop  integrated  frameworksin  the  scientific  discovery  loop.  Such  inefficiencies  increase  resource  requirements  such  as  expensive  computing  infrastructures,  significant  human  expert  efforts  and  subsequently  slows  down  scientific  discovery.In  this  thesis,  I  introduce  a  collection  of  methods  to  address  the  lack  of  precise  modeling,  lack  of  efficient  learning  methods  and  lack  of  human-in-the-loop  integrated  frameworks  in  AI-driven  scientific  discovery  workflow.  These  methods  include  automatic  physics  model  learning  from  partially  annotated  noisy  video  data,  accelerated  partial  differential  equation  (PDE)  physics  model  learning,  and  an  integrated  AI-driven  platform  for  rapid  analysis  of  experimental  video  data.  My  research  has  led  to  the  discovery  of  a  new  size  fluctuation  property  of  material  defectsexposed  to  high  temperature  and  high  irradiation  environments  such  as  inside  nuclear  reactors.  Such  discovery  is  essential  for  designing  strong  materials  that  are  critical  for  energy  applications.To  address  the  lack  of  precise  modeling  of  physics  learning  tasks,  I  developed  NeuraDiff  [1],  an  end-to-end  method  for  learning  phase  field  physics  models  from  noisy  video  data.  In  previous  learning  approaches  involving  multiple  disjoint  steps,  errors  in  one  step  can  propagate  to  another,  thus  affecting  the  accuracy  of  the  learned  physics  models.  Trial-and-error  simulation  methods  for  learning  physics  model  parameters  are  inefficient,  heavily  dependent  on  expert  intuition  and  may  not  yield  reasonably  accurate  physics  models  even  after  many  trial  iterations.  By  encoding  the  physics  model  equations  directly  into  learning,  end-to-end  NeuraDiff  framework  can  provide  ≈  100%  accurate  tracking  of  material  defects  and  yield  correct  physics  model  parameters.
■590    ▼aSchool  code:  0183.
■650  4▼aPartial  differential  equations
■650  4▼aDeep  learning
■650  4▼aDefects
■650  4▼aBack  propagation
■650  4▼aFourier  transforms
■650  4▼aGrain  growth
■650  4▼aHigh  temperature
■650  4▼aNeural  networks
■650  4▼aMicroscopy
■650  4▼aHeat
■650  4▼aCrowdsourcing
■650  4▼aHuman  error
■650  4▼aRadiation
■650  4▼aData  compression
■650  4▼aComputer  science
■650  4▼aHigh  temperature  physics
■650  4▼aMathematics
■650  4▼aThermodynamics
■690    ▼a0800
■690    ▼a0984
■690    ▼a0597
■690    ▼a0405
■690    ▼a0348
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-05B.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164966▼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
    TF12535 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.