본문

서브메뉴

A Generative Account of Latent Abstractions
A Generative Account of Latent Abstractions
A Generative Account of Latent Abstractions

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211152839
ISBN  
9798384140955
DDC  
621.3
저자명  
Xie, Sirui.
서명/저자  
A Generative Account of Latent Abstractions
발행사항  
[Sl] : University of California, Los Angeles, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
298 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
주기사항  
Advisor: Terzopoulos, Demetri;Zhu, Song-Chun.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2024.
초록/해제  
요약Abstractions are fundamental to human intelligence, extending far beyond pattern recognition. They enable the distillation and organization of complex information into structured knowledge, facilitate the succinct communication of intricate ideas, and empower us to navigate complex decision-making scenarios with consistent value prediction. The ability to abstract is particularly fascinating because abstractions are not inherently present in raw data --- they are latent variables underlying our observations. Despite the recent phenomenal advances in modeling data distributions, Generative Artificial Intelligence (GenAI) systems still lack robust principles for the autonomous emergence of latent abstractions.This dissertation studies the problem of unsupervised latent abstraction learning, focusing on developing modeling, learning, and inference methods for latent-variable generative models across diverse high-dimensional data modalities. The core premise is that by incorporating algebraic, geometric, and statistical structures into the latent space and generator, we can cultivate representations of latent variables that explain observed data in alignment with human understanding.The dissertation consists of four parts. The first three explore the generative constructs of latent abstractions for Category, Object, and Decision, respectively. Part I examines the basic structure of categories, emphasizing their symbol-vector duality. We develop a latent-variable text model with a coupling of symbols and vectors in its representations. We investigate another representation that is both discrete and continuous --- iconic symbols --- in a visual communication game. Part II enriches the abstract structure by shifting focus to object-centric abstractions in visual data. We introduce a generative model that disentangles objects from backgrounds in the latent space. We then rethink the algebraic structures of object abstractions and propose a novel metric that measures compositionality as a more generic form than disentanglement. Part III incorporates situational context by introducing a sequential decision-making aspect with trajectory data. Here, latent abstractions manifest as actions and plans. We bridge the theories of decision-making and generative modeling, proving that the inference of latent decisions enhances consistency with the model's understanding while optimizing intrinsic values. Whereas these three parts adopt the paradigm of directly learning from raw data, Part IV introduces a dialectic discussion with an alternative paradigm, Knowledge Distillation. We demonstrate how to distill from and accelerate the state-of-the-art massive-scale data-space models by re-purposing our methods and techniques for latent-variable generative modeling.Together, the contributions of this dissertation enable GenAI systems to overcome the critical bottlenecks of alignment, efficiency, and consistency in representation, inference, and decision-making.
일반주제명  
Computer engineering
일반주제명  
Computer science
키워드  
Decision-making
키워드  
Generative models
키워드  
Latent abstractions
키워드  
Generative Artificial Intelligence
기타저자  
University of California, Los Angeles Computer Science 0201
기본자료저록  
Dissertations Abstracts International. 86-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164166
■00520250211152839
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384140955
■035    ▼a(MiAaPQ)AAI31562084
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aXie,  Sirui.
■24512▼aA  Generative  Account  of  Latent  Abstractions
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a298  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-03,  Section:  B.
■500    ▼aAdvisor:  Terzopoulos,  Demetri;Zhu,  Song-Chun.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2024.
■520    ▼aAbstractions  are  fundamental  to  human  intelligence,  extending  far  beyond  pattern  recognition.  They  enable  the  distillation  and  organization  of  complex  information  into  structured  knowledge,  facilitate  the  succinct  communication  of  intricate  ideas,  and  empower  us  to  navigate  complex  decision-making  scenarios  with  consistent  value  prediction.  The  ability  to  abstract  is  particularly  fascinating  because  abstractions  are  not  inherently  present  in  raw  data  ---  they  are  latent  variables  underlying  our  observations.  Despite  the  recent  phenomenal  advances  in  modeling  data  distributions,  Generative  Artificial  Intelligence  (GenAI)  systems  still  lack  robust  principles  for  the  autonomous  emergence  of  latent  abstractions.This  dissertation  studies  the  problem  of  unsupervised  latent  abstraction  learning,  focusing  on  developing  modeling,  learning,  and  inference  methods  for  latent-variable  generative  models  across  diverse  high-dimensional  data  modalities.  The  core  premise  is  that  by  incorporating  algebraic,  geometric,  and  statistical  structures  into  the  latent  space  and  generator,  we  can  cultivate  representations  of  latent  variables  that  explain  observed  data  in  alignment  with  human  understanding.The  dissertation  consists  of  four  parts.  The  first  three  explore  the  generative  constructs  of  latent  abstractions  for  Category,  Object,  and  Decision,  respectively.  Part  I  examines  the  basic  structure  of  categories,  emphasizing  their  symbol-vector  duality.  We  develop  a  latent-variable  text  model  with  a  coupling  of  symbols  and  vectors  in  its  representations.  We  investigate  another  representation  that  is  both  discrete  and  continuous  ---  iconic  symbols  ---  in  a  visual  communication  game.  Part  II  enriches  the  abstract  structure  by  shifting  focus  to  object-centric  abstractions  in  visual  data.  We  introduce  a  generative  model  that  disentangles  objects  from  backgrounds  in  the  latent  space.  We  then  rethink  the  algebraic  structures  of  object  abstractions  and  propose  a  novel  metric  that  measures  compositionality  as  a  more  generic  form  than  disentanglement.  Part  III  incorporates  situational  context  by  introducing  a  sequential  decision-making  aspect  with  trajectory  data.  Here,  latent  abstractions  manifest  as  actions  and  plans.  We  bridge  the  theories  of  decision-making  and  generative  modeling,  proving  that  the  inference  of  latent  decisions  enhances  consistency  with  the  model's  understanding  while  optimizing  intrinsic  values.  Whereas  these  three  parts  adopt  the  paradigm  of  directly  learning  from  raw  data,  Part  IV  introduces  a  dialectic  discussion  with  an  alternative  paradigm,  Knowledge  Distillation.  We  demonstrate  how  to  distill  from  and  accelerate  the  state-of-the-art  massive-scale  data-space  models  by  re-purposing  our  methods  and  techniques  for  latent-variable  generative  modeling.Together,  the  contributions  of  this  dissertation  enable  GenAI  systems  to  overcome  the  critical  bottlenecks  of  alignment,  efficiency,  and  consistency  in  representation,  inference,  and  decision-making.
■590    ▼aSchool  code:  0031.
■650  4▼aComputer  engineering
■650  4▼aComputer  science
■653    ▼aDecision-making
■653    ▼aGenerative  models
■653    ▼aLatent  abstractions
■653    ▼aGenerative  Artificial  Intelligence
■690    ▼a0800
■690    ▼a0984
■690    ▼a0464
■71020▼aUniversity  of  California,  Los  Angeles▼bComputer  Science  0201.
■7730  ▼tDissertations  Abstracts  International▼g86-03B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164166▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    ค้นหาข้อมูลรายละเอียด

    • จองห้องพัก
    • ไม่อยู่
    • โฟลเดอร์ของฉัน
    • ขอดูแรก
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    วัสดุ
    Reg No. Call No. ตำแหน่งที่ตั้ง สถานะ ยืมข้อมูล
    TF12385 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * จองมีอยู่ในหนังสือยืม เพื่อให้การสำรองที่นั่งคลิกที่ปุ่มจองห้องพัก

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.