서브메뉴
검색
Aligning and Comparing Vision Representations to Improve Understanding and Performance
Aligning and Comparing Vision Representations to Improve Understanding and Performance
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104757
- ISBN
- 9798290652610
- DDC
- 621.3
- 서명/저자
- Aligning and Comparing Vision Representations to Improve Understanding and Performance
- 발행사항
- [Sl] : California Institute of Technology, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 266 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Perona, Pietro.
- 학위논문주기
- Thesis (Ph.D.)--California Institute of Technology, 2025.
- 초록/해제
- 요약Recent advances in large artificial intelligence (AI) models have enabled these models to perform a wide range of real-world tasks with skill levels comparable to or surpassing those of humans. In this thesis, we develop methods to compare, analyze, and align data representations from these powerful models. In Part 1, we develop methods for estimating human knowledge during a learning task and for comparing various data representations. These methods are steps towards a system designed to help us learn from AI. In Part 2, we show how aligning models can be useful in two separate domains. First, we discover and fix a misalignment in the inputs to a powerful foundation model and show how it improves performance. Second, we show that biologically inspired object manipulation tasks can be used as a training signal for learning human-aligned representations of number. Our results demonstrate the potential for alignment and comparison methods to improve the overall performance of AI models, improve our understanding of biological intelligence, and help us discover new patterns in the natural world.
- 일반주제명
- Computer engineering
- 키워드
- Real-world tasks
- 기타저자
- California Institute of Technology Biology and Biological Engineering
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358824
■00520260202104757
■006m o d
■007cr#unu||||||||
■020 ▼a9798290652610
■035 ▼a(MiAaPQ)AAI32151392
■035 ▼a(MiAaPQ)Caltech17388
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a621.3
■1001 ▼aKondapaneni, Neehar.
■24510▼aAligning and Comparing Vision Representations to Improve Understanding and Performance
■260 ▼a[Sl]▼bCalifornia Institute of Technology▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a266 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Perona, Pietro.
■5021 ▼aThesis (Ph.D.)--California Institute of Technology, 2025.
■520 ▼aRecent advances in large artificial intelligence (AI) models have enabled these models to perform a wide range of real-world tasks with skill levels comparable to or surpassing those of humans. In this thesis, we develop methods to compare, analyze, and align data representations from these powerful models. In Part 1, we develop methods for estimating human knowledge during a learning task and for comparing various data representations. These methods are steps towards a system designed to help us learn from AI. In Part 2, we show how aligning models can be useful in two separate domains. First, we discover and fix a misalignment in the inputs to a powerful foundation model and show how it improves performance. Second, we show that biologically inspired object manipulation tasks can be used as a training signal for learning human-aligned representations of number. Our results demonstrate the potential for alignment and comparison methods to improve the overall performance of AI models, improve our understanding of biological intelligence, and help us discover new patterns in the natural world.
■590 ▼aSchool code: 0037.
■650 4▼aComputer engineering
■653 ▼aReal-world tasks
■653 ▼aObject manipulation tasks
■690 ▼a0464
■690 ▼a0800
■71020▼aCalifornia Institute of Technology▼bBiology and Biological Engineering.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0037
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358824▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
