서브메뉴
검색
Parsing the Geometry of Distributed Representations
Parsing the Geometry of Distributed Representations
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211153119
- ISBN
- 9798346764144
- DDC
- 616
- 저자명
- Alleman, Matteo.
- 서명/저자
- Parsing the Geometry of Distributed Representations
- 발행사항
- [Sl] : Columbia University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 172 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Fusi, Stefano.
- 학위논문주기
- Thesis (Ph.D.)--Columbia University, 2024.
- 초록/해제
- 요약The progression of neuroscience relies on the discovery of structure in the brain. From the discovery of neurons to the structure of the potassium channel, and, in recent years, the repeated observation of remarkable geometric structure in the distributed activity of neural populations. What this population-level structure does is not written on it for anyone to read, generally speaking; many statistical and theoretical tools have had to be developed for interpretation. In these chapters, I benefit from and contribute to the growing set of tools for parsing geometries. First, my collaborators and I studied the representation of syntax in (at the time) state-of-the-art language models. Second, we sought to understand why certain geometries emerge in artificial networks. Third, we model the geometry of working memory representations to try and find why `swap errors' occur. Finally, we offer a new framework and method for discovering discrete structure in continuous representations.
- 일반주제명
- Neurosciences
- 일반주제명
- Bioinformatics
- 일반주제명
- Bioengineering
- 키워드
- Geometry
- 키워드
- Neurons
- 키워드
- Swap errors
- 기타저자
- Columbia University Neurobiology and Behavior
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017165070
■00520250211153119
■006m o d
■007cr#unu||||||||
■020 ▼a9798346764144
■035 ▼a(MiAaPQ)AAI31761236
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a616
■1001 ▼aAlleman, Matteo.
■24510▼aParsing the Geometry of Distributed Representations
■260 ▼a[Sl]▼bColumbia University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a172 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Fusi, Stefano.
■5021 ▼aThesis (Ph.D.)--Columbia University, 2024.
■520 ▼aThe progression of neuroscience relies on the discovery of structure in the brain. From the discovery of neurons to the structure of the potassium channel, and, in recent years, the repeated observation of remarkable geometric structure in the distributed activity of neural populations. What this population-level structure does is not written on it for anyone to read, generally speaking; many statistical and theoretical tools have had to be developed for interpretation. In these chapters, I benefit from and contribute to the growing set of tools for parsing geometries. First, my collaborators and I studied the representation of syntax in (at the time) state-of-the-art language models. Second, we sought to understand why certain geometries emerge in artificial networks. Third, we model the geometry of working memory representations to try and find why `swap errors' occur. Finally, we offer a new framework and method for discovering discrete structure in continuous representations.
■590 ▼aSchool code: 0054.
■650 4▼aNeurosciences
■650 4▼aBioinformatics
■650 4▼aBioengineering
■653 ▼aGeometry
■653 ▼aContinuous representations
■653 ▼aNeurons
■653 ▼aArtificial networks
■653 ▼aSwap errors
■690 ▼a0317
■690 ▼a0202
■690 ▼a0715
■71020▼aColumbia University▼bNeurobiology and Behavior.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0054
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17165070▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
