서브메뉴
검색
Latent Space Modeling for Brain Mechanisms, Language and Decision-Making
Latent Space Modeling for Brain Mechanisms, Language and Decision-Making
상세정보
- 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
- Brain mechanisms
- 키워드
- Decision-making
- 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.
