서브메뉴
검색
Right for the Right Reasons: Training Neural Networks to Be Interpretable, Robust, and Consistent with Expert Knowledge
Right for the Right Reasons: Training Neural Networks to Be Interpretable, Robust, and Consistent with Expert Knowledge
상세정보
- 자료유형
- 학위논문파일 국외
- ISBN
- 9798534680119
- DDC
- 004
- 서명/저자
- Right for the Right Reasons: Training Neural Networks to Be Interpretable, Robust, and Consistent with Expert Knowledge
- 발행사항
- [Sl] : Harvard University, 2021
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2021
- 형태사항
- 220 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
- 주기사항
- Advisor: Doshi-Velez, F.
- 학위논문주기
- Thesis (Ph.D.)--Harvard University, 2021.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 일반주제명
- Computer science
- 일반주제명
- Cancer
- 일반주제명
- Accuracy
- 일반주제명
- Datasets
- 일반주제명
- Mortality
- 일반주제명
- Christianity
- 일반주제명
- Neural networks
- 일반주제명
- Classification
- 일반주제명
- Urine
- 일반주제명
- Algorithms
- 일반주제명
- Atheism
- 일반주제명
- Learning
- 일반주제명
- Creatinine
- 키워드
- Interpretability
- 키워드
- Machine learning
- 키워드
- Robustness
- 기타저자
- Harvard University Engineering and Applied Sciences - Computer Science
- 기본자료저록
- Dissertations Abstracts International. 83-02B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008220131s2021 us c eng d■020 ▼a9798534680119
■035 ▼a(MiAaPQ)AAI28496231
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aRoss, Andrew Slavin.▼0(orcid)0000-0002-2368-6979
■24510▼aRight for the Right Reasons: Training Neural Networks to Be Interpretable, Robust, and Consistent with Expert Knowledge
■260 ▼a[Sl]▼bHarvard University▼c2021
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2021
■300 ▼a220 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 83-02, Section: B.
■500 ▼aAdvisor: Doshi-Velez, F.
■5021 ▼aThesis (Ph.D.)--Harvard University, 2021.
■506 ▼aThis item must not be sold to any third party vendors.
■590 ▼aSchool code: 0084.
■650 4▼aComputer science
■650 4▼aCancer
■650 4▼aAccuracy
■650 4▼aDatasets
■650 4▼aMortality
■650 4▼aChristianity
■650 4▼aNeural networks
■650 4▼aClassification
■650 4▼aUrine
■650 4▼aAlgorithms
■650 4▼aAtheism
■650 4▼aLearning
■650 4▼aCreatinine
■653 ▼aInterpretability
■653 ▼aMachine learning
■653 ▼aRepresentation learning
■653 ▼aRobustness
■690 ▼a0984
■71020▼aHarvard University▼bEngineering and Applied Sciences - Computer Science.
■7730 ▼tDissertations Abstracts International▼g83-02B.
■773 ▼tDissertation Abstract International
■790 ▼a0084
■791 ▼aPh.D.
■792 ▼a2021
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16051993▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202202▼f2022
