본문

서브메뉴

Neural Dynamics for Science: The Symbiosis of Deep Graph Learning and Differential Equations
Neural Dynamics for Science: The Symbiosis of Deep Graph Learning and Differential Equatio...
Neural Dynamics for Science: The Symbiosis of Deep Graph Learning and Differential Equations

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152005
ISBN  
9798382837741
DDC  
004
저자명  
Huang, Zijie.
서명/저자  
Neural Dynamics for Science: The Symbiosis of Deep Graph Learning and Differential Equations
발행사항  
[Sl] : University of California, Los Angeles, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
159 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Sun, Yizhou;Wang, Wei.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2024.
초록/해제  
요약Many scientific problems require a deep understanding of internal structures and complex dynamics, spanning physical interactions within molecules, brain networks, and beyond. These problems can be formulated as modeling interacting dynamical systems using graphs, which represent entities as nodes and their relationship as edges. Traditionally, the dynamics of interacting systems are described by ordinary differential equations (ODEs), offering continuous and interpretable solutions but requiring significant domain expertise. Recent data-driven approaches such as Graph Neural Networks (GNNs) learn system dynamics from observational data, which however, struggle with long-term predictions and irregular observations due to their discrete dynamics.My research aims to develop novel frameworks that bridge these two worlds, i.e. combining the learning power of neural networks (NNs) with the symbolic knowledge encoded in ODEs. In contrast with discrete models, such methods provide a principled approach to model continuous dynamical systems, from synthetic simulations to real-world scenarios like brain network analysis and COVID-19 prediction. Building upon this, I have further strengthened its power in three key areas: 1.) integrating data-driven inductive biases like energy conservation law; 2.) enhancing generalization ability; 3.) enabling causal decision-making. By merging deep graph learning with differential equations, I believe my research will pave the way for breakthroughs in symbolic deep learning for scientific discovery. 
일반주제명  
Computer science
일반주제명  
Computer engineering
키워드  
Graph Neural Networks
키워드  
Ordinary differential equations
키워드  
COVID-19
키워드  
Deep graph learning
키워드  
Brain networks
기타저자  
University of California, Los Angeles Computer Science 0201
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162378
■00520250211152005
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382837741
■035    ▼a(MiAaPQ)AAI31330475
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aHuang,  Zijie.
■24510▼aNeural  Dynamics  for  Science:  The  Symbiosis  of  Deep  Graph  Learning  and  Differential  Equations
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a159  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Sun,  Yizhou;Wang,  Wei.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2024.
■520    ▼aMany  scientific  problems  require  a  deep  understanding  of  internal  structures  and  complex  dynamics,  spanning  physical  interactions  within  molecules,  brain  networks,  and  beyond.  These  problems  can  be  formulated  as  modeling  interacting  dynamical  systems  using  graphs,  which  represent  entities  as  nodes  and  their  relationship  as  edges.  Traditionally,  the  dynamics  of  interacting  systems  are  described  by  ordinary  differential  equations  (ODEs),  offering  continuous  and  interpretable  solutions  but  requiring  significant  domain  expertise.  Recent  data-driven  approaches  such  as  Graph  Neural  Networks  (GNNs)  learn  system  dynamics  from  observational  data,  which  however,  struggle  with  long-term  predictions  and  irregular  observations  due  to  their  discrete  dynamics.My  research  aims  to  develop  novel  frameworks  that  bridge  these  two  worlds,  i.e.  combining  the  learning  power  of  neural  networks  (NNs)  with  the  symbolic  knowledge  encoded  in  ODEs.  In  contrast  with  discrete  models,  such  methods  provide  a  principled  approach  to  model  continuous  dynamical  systems,  from  synthetic  simulations  to  real-world  scenarios  like  brain  network  analysis  and  COVID-19  prediction.  Building  upon  this,  I  have  further  strengthened  its  power  in  three  key  areas:  1.)  integrating  data-driven  inductive  biases  like  energy  conservation  law;  2.)  enhancing  generalization  ability;  3.)  enabling  causal  decision-making.  By  merging  deep  graph  learning  with  differential  equations,  I  believe  my  research  will  pave  the  way  for  breakthroughs  in  symbolic  deep  learning  for  scientific  discovery. 
■590    ▼aSchool  code:  0031.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■653    ▼aGraph  Neural  Networks
■653    ▼aOrdinary  differential  equations
■653    ▼aCOVID-19
■653    ▼aDeep  graph  learning
■653    ▼aBrain  networks
■690    ▼a0984
■690    ▼a0464
■71020▼aUniversity  of  California,  Los  Angeles▼bComputer  Science  0201.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162378▼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
    TF13674 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.