서브메뉴
검색
Reliable Multimodal Models
Reliable Multimodal Models
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152753
- ISBN
- 9798384448761
- DDC
- 004
- 저자명
- Petryk, Suzanne.
- 서명/저자
- Reliable Multimodal Models
- 발행사항
- [Sl] : University of California, Berkeley, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 136 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
- 주기사항
- Advisor: Gonzalez, Joseph E.;Darrell, Trevor.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Berkeley, 2024.
- 초록/해제
- 요약Before deploying a machine learning model in a real application, it is important to ensure its reliability - this can take many forms, yet is broadly defined as operating without failure. For instance, an incorrect prediction from a model could have a myriad of negative downstream effects, especially if a user has placed trust in the model or if the error is consumed and propagated by automated agents. Multimodal models are growing in their capabilities and applications, yet research into the unique challenges they pose around reliability has been limited.In this thesis, I cover my work towards improving reliability in the context of multimodal (vision + language) models. This is approached from three different axes: addressing visual biases via model explainability, learning better confidence estimates to abstain from answering questions with high uncertainty as well as reducing hallucinations in generated text, and investigating the contribution of language priors to caption error. In these works, I also present new evaluation frameworks that define particular areas of reliability. As machine learning models take a larger role in our society, carefully measuring and improving reliability becomes more important than ever.
- 일반주제명
- Computer science
- 키워드
- Caption errors
- 기타저자
- University of California, Berkeley Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-04B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017163791
■00520250211152753
■006m o d
■007cr#unu||||||||
■020 ▼a9798384448761
■035 ▼a(MiAaPQ)AAI31555639
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aPetryk, Suzanne.
■24510▼aReliable Multimodal Models
■260 ▼a[Sl]▼bUniversity of California, Berkeley▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a136 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-04, Section: B.
■500 ▼aAdvisor: Gonzalez, Joseph E.;Darrell, Trevor.
■5021 ▼aThesis (Ph.D.)--University of California, Berkeley, 2024.
■520 ▼aBefore deploying a machine learning model in a real application, it is important to ensure its reliability - this can take many forms, yet is broadly defined as operating without failure. For instance, an incorrect prediction from a model could have a myriad of negative downstream effects, especially if a user has placed trust in the model or if the error is consumed and propagated by automated agents. Multimodal models are growing in their capabilities and applications, yet research into the unique challenges they pose around reliability has been limited.In this thesis, I cover my work towards improving reliability in the context of multimodal (vision + language) models. This is approached from three different axes: addressing visual biases via model explainability, learning better confidence estimates to abstain from answering questions with high uncertainty as well as reducing hallucinations in generated text, and investigating the contribution of language priors to caption error. In these works, I also present new evaluation frameworks that define particular areas of reliability. As machine learning models take a larger role in our society, carefully measuring and improving reliability becomes more important than ever.
■590 ▼aSchool code: 0028.
■650 4▼aComputer science
■653 ▼aMachine learning model
■653 ▼aCaption errors
■653 ▼aMultimodal models
■690 ▼a0984
■690 ▼a0800
■71020▼aUniversity of California, Berkeley▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-04B.
■790 ▼a0028
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163791▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
