본문

서브메뉴

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

상세정보

자료유형  
 학위논문
Control Number  
0017161961
International Standard Book Number  
9798382762388
Dewey Decimal Classification Number  
004
Main Entry-Personal Name  
Jiang, Song.
Publication, Distribution, etc. (Imprint  
[S.l.] : University of California, Los Angeles., 2024
Publication, Distribution, etc. (Imprint  
Ann Arbor : ProQuest Dissertations & Theses, 2024
Physical Description  
134 p.
General Note  
Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
General Note  
Advisor: Sun, Yizhou.
Dissertation Note  
Thesis (Ph.D.)--University of California, Los Angeles, 2024.
Summary, Etc.  
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. 
Subject Added Entry-Topical Term  
Computer science.
Subject Added Entry-Topical Term  
Engineering.
Subject Added Entry-Topical Term  
Information technology.
Index Term-Uncontrolled  
Deep learning
Index Term-Uncontrolled  
Recurrent neural networks
Index Term-Uncontrolled  
Dynamical systems
Index Term-Uncontrolled  
Sequential data
Index Term-Uncontrolled  
Deep neural networks
Added Entry-Corporate Name  
University of California, Los Angeles Computer Science 0201
Host Item Entry  
Dissertations Abstracts International. 85-11B.
Electronic Location and Access  
로그인을 한후 보실 수 있는 자료입니다.
Control Number  
joongbu:656086

MARC

 008250224s2024        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[S.l.]▼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


    New Books MORE
    Related books MORE
    최근 3년간 통계입니다.

    詳細情報

    • 予約
    • 캠퍼스간 도서대출
    • 서가에 없는 책 신고
    • 私のフォルダ
    資料
    登録番号 請求記号 場所 ステータス 情報を貸す
    TQ0032208 T   원문자료 열람가능/출력가능 열람가능/출력가능
    마이폴더 부재도서신고

    *ご予約は、借入帳でご利用いただけます。予約をするには、予約ボタンをクリックしてください

    해당 도서를 다른 이용자가 함께 대출한 도서

    Related books

    Related Popular Books

    도서위치