서브메뉴
검색
Metrics and Evaluation for Socially Positive Systems
Metrics and Evaluation for Socially Positive Systems
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105112
- ISBN
- 9798293893263
- DDC
- 310
- 서명/저자
- Metrics and Evaluation for Socially Positive Systems
- 발행사항
- [Sl] : University of California, Berkeley, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 83 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-04, Section: A.
- 주기사항
- Advisor: Hooker, Giles;Stark, Philip.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Berkeley, 2025.
- 초록/해제
- 요약As technology and society progress, systems continue to become more complex and, consequently, more opaque. With increased complexity and opacity comes an increased risk of negative outcomes without the potential for recourse. How do we ensure that complex systems are socially positive? Here, I show that measurement and evaluation are important tools in engendering socially positive systems. Measurement can enable quantification of important qualities, and we can use measurement to evaluate systems for desired behavior. My work applies measurement and evaluation concepts to machine learning explainability, forensic DNA software, and fairness in decision making. In doing so, I demonstrate several ways measurement and evaluation can improve our understanding of system behavior and occasionally can directly improve systems themselves.
- 일반주제명
- Statistics
- 일반주제명
- Computer science
- 일반주제명
- Forensic sciences
- 키워드
- Machine learning
- 키워드
- Metrics
- 키워드
- System behavior
- 기타저자
- University of California, Berkeley Statistics
- 기본자료저록
- Dissertations Abstracts International. 87-04A.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359387
■00520260202105112
■006m o d
■007cr#unu||||||||
■020 ▼a9798293893263
■035 ▼a(MiAaPQ)AAI32237147
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a310
■1001 ▼aAsemota, Alexander.
■24510▼aMetrics and Evaluation for Socially Positive Systems
■260 ▼a[Sl]▼bUniversity of California, Berkeley▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a83 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-04, Section: A.
■500 ▼aAdvisor: Hooker, Giles;Stark, Philip.
■5021 ▼aThesis (Ph.D.)--University of California, Berkeley, 2025.
■520 ▼aAs technology and society progress, systems continue to become more complex and, consequently, more opaque. With increased complexity and opacity comes an increased risk of negative outcomes without the potential for recourse. How do we ensure that complex systems are socially positive? Here, I show that measurement and evaluation are important tools in engendering socially positive systems. Measurement can enable quantification of important qualities, and we can use measurement to evaluate systems for desired behavior. My work applies measurement and evaluation concepts to machine learning explainability, forensic DNA software, and fairness in decision making. In doing so, I demonstrate several ways measurement and evaluation can improve our understanding of system behavior and occasionally can directly improve systems themselves.
■590 ▼aSchool code: 0028.
■650 4▼aStatistics
■650 4▼aComputer science
■650 4▼aForensic sciences
■653 ▼aMachine learning
■653 ▼aMetrics
■653 ▼aSocially positive systems
■653 ▼aSystem behavior
■690 ▼a0463
■690 ▼a0774
■690 ▼a0984
■71020▼aUniversity of California, Berkeley▼bStatistics.
■7730 ▼tDissertations Abstracts International▼g87-04A.
■790 ▼a0028
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359387▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
