본문

서브메뉴

Latent Space Modeling for Brain Mechanisms, Language and Decision-Making
Latent Space Modeling for Brain Mechanisms, Language and Decision-Making
Latent Space Modeling for Brain Mechanisms, Language and Decision-Making

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202103625
ISBN  
9798315777496
DDC  
310
저자명  
Xu, Dehong.
서명/저자  
Latent Space Modeling for Brain Mechanisms, Language and Decision-Making
발행사항  
[Sl] : University of California, Los Angeles, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
213 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
주기사항  
Advisor: Wu, Ying Nian.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2025.
초록/해제  
요약This thesis explores the theoretical foundations and applications of latent space modeling across three interconnected domains: brain mechanisms, language processing, and decision-making. The central proposition is that latent space representations-abstract encodings that capture underlying structure in complex data-offer a unified computational framework for understanding both biological and artificial intelligence.The first part of this work investigates spatial cognition in the brain, reconceptualizing hippocampal place cells as collective position embeddings that encode multi-scale transition probabilities through inner products. This novel perspective reveals how the brain might efficiently represent navigational information, with latent vectors approximating symmetric random walk transition kernels. Through mathematical analysis and computational modeling, I demonstrate that hexagonal grid patterns emerge naturally as the optimal solution for maximally distance-preserving embeddings. These models successfully reproduce key neurobiological phenomena, including scale hierarchies along the dorsoventral axis, place field remapping, and preplay-like shortcut discovery.Building on these neurally-inspired principles, I then develop two innovative frameworks for artificial intelligence. The Latent Thought Language Model (LTM) incorporates explicit latent thought vectors that guide autoregressive token generation, creating a structured design space with additional scaling dimensions beyond traditional language models. This approach demonstrates superior sample and parameter efficiency while exhibiting emergent in-context reasoning capabilities. The Latent Plan Transformer (LPT) extends these concepts to sequential decision-making, employing a latent variable to connect trajectory generation with expected returns, enabling planning as latent space inference without reliance on step-wise rewards.Across these diverse applications, common computational principles emerge: the importance of multi-scale representations, the efficiency of latent abstractions for capturing complex relationships, and the power of posterior inference for integrating contextual information. This thesis demonstrates that latent space modeling provides a compelling bridge between biological and digital intelligence, offering insights into both how the brain computes and how we might build more capable artificial systems that emulate aspects of human cognition.
일반주제명  
Statistics
일반주제명  
Neurosciences
일반주제명  
Information technology
키워드  
Latent space modeling
키워드  
Brain mechanisms
키워드  
Decision-making
키워드  
Latent Thought Language Model
키워드  
Latent Plan Transformer
기타저자  
University of California, Los Angeles Statistics 0891
기본자료저록  
Dissertations Abstracts International. 86-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357970
■00520260202103625
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798315777496
■035    ▼a(MiAaPQ)AAI32046146
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aXu,  Dehong.
■24510▼aLatent  Space  Modeling  for  Brain  Mechanisms,  Language  and  Decision-Making
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a213  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  B.
■500    ▼aAdvisor:  Wu,  Ying  Nian.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2025.
■520    ▼aThis  thesis  explores  the  theoretical  foundations  and  applications  of  latent  space  modeling  across  three  interconnected  domains:  brain  mechanisms,  language  processing,  and  decision-making.  The  central  proposition  is  that  latent  space  representations-abstract  encodings  that  capture  underlying  structure  in  complex  data-offer  a  unified  computational  framework  for  understanding  both  biological  and  artificial  intelligence.The  first  part  of  this  work  investigates  spatial  cognition  in  the  brain,  reconceptualizing  hippocampal  place  cells  as  collective  position  embeddings  that  encode  multi-scale  transition  probabilities  through  inner  products.  This  novel  perspective  reveals  how  the  brain  might  efficiently  represent  navigational  information,  with  latent  vectors  approximating  symmetric  random  walk  transition  kernels.  Through  mathematical  analysis  and  computational  modeling,  I  demonstrate  that  hexagonal  grid  patterns  emerge  naturally  as  the  optimal  solution  for  maximally  distance-preserving  embeddings.  These  models  successfully  reproduce  key  neurobiological  phenomena,  including  scale  hierarchies  along  the  dorsoventral  axis,  place  field  remapping,  and  preplay-like  shortcut  discovery.Building  on  these  neurally-inspired  principles,  I  then  develop  two  innovative  frameworks  for  artificial  intelligence.  The  Latent  Thought  Language  Model  (LTM)  incorporates  explicit  latent  thought  vectors  that  guide  autoregressive  token  generation,  creating  a  structured  design  space  with  additional  scaling  dimensions  beyond  traditional  language  models.  This  approach  demonstrates  superior  sample  and  parameter  efficiency  while  exhibiting  emergent  in-context  reasoning  capabilities.  The  Latent  Plan  Transformer  (LPT)  extends  these  concepts  to  sequential  decision-making,  employing  a  latent  variable  to  connect  trajectory  generation  with  expected  returns,  enabling  planning  as  latent  space  inference  without  reliance  on  step-wise  rewards.Across  these  diverse  applications,  common  computational  principles  emerge:  the  importance  of  multi-scale  representations,  the  efficiency  of  latent  abstractions  for  capturing  complex  relationships,  and  the  power  of  posterior  inference  for  integrating  contextual  information.  This  thesis  demonstrates  that  latent  space  modeling  provides  a  compelling  bridge  between  biological  and  digital  intelligence,  offering  insights  into  both  how  the  brain  computes  and  how  we  might  build  more  capable  artificial  systems  that  emulate  aspects  of  human  cognition.
■590    ▼aSchool  code:  0031.
■650  4▼aStatistics
■650  4▼aNeurosciences
■650  4▼aInformation  technology
■653    ▼aLatent  space  modeling
■653    ▼aBrain  mechanisms
■653    ▼aDecision-making
■653    ▼aLatent  Thought  Language  Model
■653    ▼aLatent  Plan  Transformer
■690    ▼a0463
■690    ▼a0489
■690    ▼a0800
■690    ▼a0317
■71020▼aUniversity  of  California,  Los  Angeles▼bStatistics  0891.
■7730  ▼tDissertations  Abstracts  International▼g86-11B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357970▼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

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF17240 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.