서브메뉴
검색
Geometric Representation Learning for Accelerated Design Analysis in Data-Scarce Environments
Geometric Representation Learning for Accelerated Design Analysis in Data-Scarce Environments
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103503
- ISBN
- 9798288853074
- DDC
- 741
- 저자명
- Chen, Yu-hsuan.
- 서명/저자
- Geometric Representation Learning for Accelerated Design Analysis in Data-Scarce Environments
- 발행사항
- [Sl] : Carnegie Mellon University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 148 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
- 주기사항
- Advisor: Cagan, Jonathan;Kara, Levent Burak.
- 학위논문주기
- Thesis (Ph.D.)--Carnegie Mellon University, 2025.
- 초록/해제
- 요약Geometric representation learning can address challenges that were previously difficult for data-driven methods due to data scarcity. Geometry data scarcity can be mitigated through grammar- based modeling or modality conversion, while label scarcity can be tackled in two ways. First, when indirect, easily accessible labels are available, weakly supervised learning allows for the extraction of high-level design features. Second, in the complete absence of labels, inter- modality geometric pretraining improves design quantity estimation in few-shot scenarios. This approach is effective for tasks involving scalar values, temporal histories, and scalar fields. Furthermore, customized training strategies can be tailored to capture and process domain-specific geometries, such as thin shells and geometries with fine-scale details.
- 일반주제명
- Design
- 일반주제명
- Mechanical engineering
- 일반주제명
- Computer science
- 키워드
- Computer vision
- 키워드
- Machine learning
- 기타저자
- Carnegie Mellon University Mechanical Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-01B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357377
■00520260202103503
■006m o d
■007cr#unu||||||||
■020 ▼a9798288853074
■035 ▼a(MiAaPQ)AAI32001811
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a741
■1001 ▼aChen, Yu-hsuan.▼0(orcid)0009-0008-5436-0403
■24510▼aGeometric Representation Learning for Accelerated Design Analysis in Data-Scarce Environments
■260 ▼a[Sl]▼bCarnegie Mellon University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a148 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-01, Section: B.
■500 ▼aAdvisor: Cagan, Jonathan;Kara, Levent Burak.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2025.
■520 ▼aGeometric representation learning can address challenges that were previously difficult for data-driven methods due to data scarcity. Geometry data scarcity can be mitigated through grammar- based modeling or modality conversion, while label scarcity can be tackled in two ways. First, when indirect, easily accessible labels are available, weakly supervised learning allows for the extraction of high-level design features. Second, in the complete absence of labels, inter- modality geometric pretraining improves design quantity estimation in few-shot scenarios. This approach is effective for tasks involving scalar values, temporal histories, and scalar fields. Furthermore, customized training strategies can be tailored to capture and process domain-specific geometries, such as thin shells and geometries with fine-scale details.
■590 ▼aSchool code: 0041.
■650 4▼aDesign
■650 4▼aMechanical engineering
■650 4▼aComputer science
■653 ▼aComputer vision
■653 ▼aComputer-aided design
■653 ▼aData-driven design
■653 ▼aMachine learning
■653 ▼aRepresentation learning
■653 ▼aSelf-supervised learning
■690 ▼a0800
■690 ▼a0389
■690 ▼a0548
■690 ▼a0984
■71020▼aCarnegie Mellon University▼bMechanical Engineering.
■7730 ▼tDissertations Abstracts International▼g87-01B.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357377▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
