본문

서브메뉴

Towards Causally-Aware Dynamical System Prediction
Towards Causally-Aware Dynamical System Prediction
Towards Causally-Aware Dynamical System Prediction

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151508
ISBN  
9798382762388
DDC  
004
저자명  
Jiang, Song.
서명/저자  
Towards Causally-Aware Dynamical System Prediction
발행사항  
[Sl] : University of California, Los Angeles, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
134 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
주기사항  
Advisor: Sun, Yizhou.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2024.
초록/해제  
요약Understanding and predicting the dynamics is one fundamental problem that supports various real-world applications. Deep learning dynamical models such as recurrent neural networks (RNNs) and Transformer show powerful expressiveness in modeling sequential data. However, pure deep learning models lack appropriate inductive bias for dynamics, which limits their potential for more accurate dynamic predictions.This dissertation aims to enhance deep neural networks' capability of modeling dynamics. My research starts by injecting physical law as prior knowledge into deep nets, with the finding that such prior knowledge shapes the predicted trajectory desirably and therefore achieves more accurate forecasting. However, such physical law is not available for more general and complicated dynamics, such as retail time series, and energy consumption sequence. To this end, we propose to use the Fourier series instead of task-specific rules as a more general inductive bias to capture the periodicity. Unfortunately, either specific physical law or general periodic series still just learns the association between historical observations and the future series. However, answering counterfactual questions like "Would the community protection be better had a different group of people gotten vaccinated first?" is one key problem for decision-making in dynamical systems. A dynamical is naturally represented by a graph, where units are nodes and the interactions among them are edges. The second part of my research focuses on how to answer causal questions on graphs and then extend to general dynamical systems. 
일반주제명  
Computer science
일반주제명  
Engineering
일반주제명  
Information technology
키워드  
Deep learning
키워드  
Recurrent neural networks
키워드  
Dynamical systems
키워드  
Sequential data
키워드  
Deep neural networks
기타저자  
University of California, Los Angeles Computer Science 0201
기본자료저록  
Dissertations Abstracts International. 85-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161961
■00520250211151508
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382762388
■035    ▼a(MiAaPQ)AAI31299308
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aJiang,  Song.
■24510▼aTowards  Causally-Aware  Dynamical  System  Prediction
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a134  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-11,  Section:  B.
■500    ▼aAdvisor:  Sun,  Yizhou.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2024.
■520    ▼aUnderstanding  and  predicting  the  dynamics  is  one  fundamental  problem  that  supports  various  real-world  applications.  Deep  learning  dynamical  models  such  as  recurrent  neural  networks  (RNNs)  and  Transformer  show  powerful  expressiveness  in  modeling  sequential  data.  However,  pure  deep  learning  models  lack  appropriate  inductive  bias  for  dynamics,  which  limits  their  potential  for  more  accurate  dynamic  predictions.This  dissertation  aims  to  enhance  deep  neural  networks'  capability  of  modeling  dynamics.  My  research  starts  by  injecting  physical  law  as  prior  knowledge  into  deep  nets,  with  the  finding  that  such  prior  knowledge  shapes  the  predicted  trajectory  desirably  and  therefore  achieves  more  accurate  forecasting.  However,  such  physical  law  is  not  available  for  more  general  and  complicated  dynamics,  such  as  retail  time  series,  and  energy  consumption  sequence.  To  this  end,  we  propose  to  use  the  Fourier  series  instead  of  task-specific  rules  as  a  more  general  inductive  bias  to  capture  the  periodicity.  Unfortunately,  either  specific  physical  law  or  general  periodic  series  still  just  learns  the  association  between  historical  observations  and  the  future  series.  However,  answering  counterfactual  questions  like  "Would  the  community  protection  be  better  had  a  different  group  of  people  gotten  vaccinated  first?"  is  one  key  problem  for  decision-making  in  dynamical  systems.  A  dynamical  is  naturally  represented  by  a  graph,  where  units  are  nodes  and  the  interactions  among  them  are  edges.  The  second  part  of  my  research  focuses  on  how  to  answer  causal  questions  on  graphs  and  then  extend  to  general  dynamical  systems. 
■590    ▼aSchool  code:  0031.
■650  4▼aComputer  science
■650  4▼aEngineering
■650  4▼aInformation  technology
■653    ▼aDeep  learning
■653    ▼aRecurrent  neural  networks
■653    ▼aDynamical  systems
■653    ▼aSequential  data
■653    ▼aDeep  neural  networks
■690    ▼a0984
■690    ▼a0489
■690    ▼a0800
■690    ▼a0537
■71020▼aUniversity  of  California,  Los  Angeles▼bComputer  Science  0201.
■7730  ▼tDissertations  Abstracts  International▼g85-11B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161961▼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
    TF12242 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.