서브메뉴
검색
Towards Structured Intelligence for Sequence Modeling
Towards Structured Intelligence for Sequence Modeling
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105624
- ISBN
- 9798265429629
- DDC
- 500
- 서명/저자
- Towards Structured Intelligence for Sequence Modeling
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 163 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Fox, Emily.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약Learning, for both human and machine, is a search for explanations that fit our observations. This process is shaped by the priors, biases, and inductive assumptions embedded in the structure of our hypothesis space. In this thesis, we explore how introducing the right structure can guide machine learning in sequence modeling tasks. We begin with a real-world problem of modeling glucose control using free-living continuous glucose monitor data. By embedding mechanistic physiological models into the learning process, we constrain the hypothesis space to reflect our understanding of how the body regulates glucose, producing interpretable and clinically meaningful representations of glycemic control. We then turn to generic sequence modeling, where we study two ways to incorporate structure through memory. One approach introduces multiresolution memory as an inductive bias that captures hierarchical patterns common in sequence data, yielding a parameter-efficient neural network grounded in wavelet theory. Another offers a unifying framework for understanding and deriving modern neural sequence models, such as softmax attention and state-space models, viewing them as implicit algorithms for associative memory and retrieval. This thesis takes a step towards structured intelligence for sequence modeling, showing how principled architectural designs, whether drawn from domain knowledge or memory mechanisms, can produce models that are more interpretable and effective.
- 일반주제명
- Decomposition
- 일반주제명
- Glucose
- 일반주제명
- Diabetes
- 일반주제명
- Deep learning
- 일반주제명
- Wavelet transforms
- 일반주제명
- Insulin
- 일반주제명
- Neural networks
- 일반주제명
- Mathematics
- 일반주제명
- Medicine
- 일반주제명
- Pharmaceutical sciences
- 일반주제명
- Public health
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017360826
■00520260202105624
■006m o d
■007cr#unu||||||||
■020 ▼a9798265429629
■035 ▼a(MiAaPQ)AAI32316541
■035 ▼a(MiAaPQ)Stanfordng584zt1322
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a500
■1001 ▼aWang, Ke Alexander.
■24510▼aTowards Structured Intelligence for Sequence Modeling
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a163 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Fox, Emily.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aLearning, for both human and machine, is a search for explanations that fit our observations. This process is shaped by the priors, biases, and inductive assumptions embedded in the structure of our hypothesis space. In this thesis, we explore how introducing the right structure can guide machine learning in sequence modeling tasks. We begin with a real-world problem of modeling glucose control using free-living continuous glucose monitor data. By embedding mechanistic physiological models into the learning process, we constrain the hypothesis space to reflect our understanding of how the body regulates glucose, producing interpretable and clinically meaningful representations of glycemic control. We then turn to generic sequence modeling, where we study two ways to incorporate structure through memory. One approach introduces multiresolution memory as an inductive bias that captures hierarchical patterns common in sequence data, yielding a parameter-efficient neural network grounded in wavelet theory. Another offers a unifying framework for understanding and deriving modern neural sequence models, such as softmax attention and state-space models, viewing them as implicit algorithms for associative memory and retrieval. This thesis takes a step towards structured intelligence for sequence modeling, showing how principled architectural designs, whether drawn from domain knowledge or memory mechanisms, can produce models that are more interpretable and effective.
■590 ▼aSchool code: 0212.
■650 4▼aDecomposition
■650 4▼aGlucose
■650 4▼aDiabetes
■650 4▼aDeep learning
■650 4▼aWavelet transforms
■650 4▼aInsulin
■650 4▼aNeural networks
■650 4▼aMathematics
■650 4▼aMedicine
■650 4▼aPharmaceutical sciences
■650 4▼aPublic health
■690 ▼a0800
■690 ▼a0405
■690 ▼a0564
■690 ▼a0572
■690 ▼a0573
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360826▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


