본문

서브메뉴

Transitional Information Extraction
Transitional Information Extraction
Transitional Information Extraction

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105601
ISBN  
9798265404947
DDC  
000
저자명  
Benkert, Ryan.
서명/저자  
Transitional Information Extraction
발행사항  
[Sl] : Georgia Institute of Technology, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
155 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: AlRegib, Ghassan.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2024.
초록/해제  
요약The practical deployment of neural networks is contingent on their ability to extract information beyond a predictive output. Unfortunately, neural networks do not naturally implement this property and are optimized to compress information unrelated to the target application. For this purpose, extracting information from neural networks is frequently coupled with optimization constraints or with utilizing a collection of neural networks that require several iterative forward passes. While each of these paradigms show promising results, each comes with a set of drawbacks that limit their deployment in the real world: constraints can result in a performance degradation on the application while iterative approaches require several forward passes.In this thesis, we address these limitations by realizing iterative information extraction as a sub-category of a broader family of paradigms transitional information extraction. A key observation we make in this thesis is that the source representations are generalizable beyond several forward passes and can be implemented within a single neural network. Our approach is grounded in a detailed analysis of existing paradigms where we identify causes of performance decline for application constraints, as well as implication of limited data on the information extraction capabilities of the network. Our study results in a suite of algorithms that implement transitional information extraction. We study transitional information extraction within the context of uncertainty estimation. Here, we develop TULIP which leverages intermediate representations to preserve information as data points traverse the network. We further investigate active learning where we consider using prediction switches to extract different information from the neural network. We extract information related to robustness with GauSS, performance regression with Rose, and spatial regions of interest with ATLAS. All of our algorithms are supported with extensive experiments on established benchmarks within the field of active learning and uncertainty estimation.
일반주제명  
Toads
일반주제명  
Deep learning
일반주제명  
Entropy
일반주제명  
Neural networks
일반주제명  
Benchmarks
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017360648
■00520260202105601
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798265404947
■035    ▼a(MiAaPQ)AAI32315974
■035    ▼a(MiAaPQ)GeorgiaTech75284
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a000
■1001  ▼aBenkert,  Ryan.
■24510▼aTransitional  Information  Extraction
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a155  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  AlRegib,  Ghassan.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2024.
■520    ▼aThe  practical  deployment  of  neural  networks  is  contingent  on  their  ability  to  extract  information  beyond  a  predictive  output.  Unfortunately,  neural  networks  do  not  naturally  implement  this  property  and  are  optimized  to  compress  information  unrelated  to  the  target  application.  For  this  purpose,  extracting  information  from  neural  networks  is  frequently  coupled  with  optimization  constraints  or  with  utilizing  a  collection  of  neural  networks  that  require  several  iterative  forward  passes.  While  each  of  these  paradigms  show  promising  results,  each  comes  with  a  set  of  drawbacks  that  limit  their  deployment  in  the  real  world:  constraints  can  result  in  a  performance  degradation  on  the  application  while  iterative  approaches  require  several  forward  passes.In  this  thesis,  we  address  these  limitations  by  realizing  iterative  information  extraction  as  a  sub-category  of  a  broader  family  of  paradigms  transitional  information  extraction.  A  key  observation  we  make  in  this  thesis  is  that  the  source  representations  are  generalizable  beyond  several  forward  passes  and  can  be  implemented  within  a  single  neural  network.  Our  approach  is  grounded  in  a  detailed  analysis  of  existing  paradigms  where  we  identify  causes  of  performance  decline  for  application  constraints,  as  well  as  implication  of  limited  data  on  the  information  extraction  capabilities  of  the  network.  Our  study  results  in  a  suite  of  algorithms  that  implement  transitional  information  extraction.  We  study  transitional  information  extraction  within  the  context  of  uncertainty  estimation.  Here,  we  develop  TULIP  which  leverages  intermediate  representations  to  preserve  information  as  data  points  traverse  the  network.  We  further  investigate  active  learning  where  we  consider  using  prediction  switches  to  extract  different  information  from  the  neural  network.  We  extract  information  related  to  robustness  with  GauSS,  performance  regression  with  Rose,  and  spatial  regions  of  interest  with  ATLAS.  All  of  our  algorithms  are  supported  with  extensive  experiments  on  established  benchmarks  within  the  field  of  active  learning  and  uncertainty  estimation.
■590    ▼aSchool  code:  0078.
■650  4▼aToads
■650  4▼aDeep  learning
■650  4▼aEntropy
■650  4▼aNeural  networks
■650  4▼aBenchmarks
■690    ▼a0800
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360648▼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
    TF17455 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.