서브메뉴
검색
Deep Thinking Systems: Logical Extrapolation With Recurrent Neural Networks- [electronic resource]
Deep Thinking Systems: Logical Extrapolation With Recurrent Neural Networks- [electronic resource]
상세정보
- 자료유형
- 학위논문파일 국외
- 최종처리일시
- 20240214100112
- ISBN
- 9798379761950
- DDC
- 004
- 서명/저자
- Deep Thinking Systems: Logical Extrapolation With Recurrent Neural Networks - [electronic resource]
- 발행사항
- [S.l.]: : University of Maryland, College Park., 2023
- 발행사항
- Ann Arbor : : ProQuest Dissertations & Theses,, 2023
- 형태사항
- 1 online resource(124 p.)
- 주기사항
- Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
- 주기사항
- Advisor: Goldstein, Tom.
- 학위논문주기
- Thesis (Ph.D.)--University of Maryland, College Park, 2023.
- 사용제한주기
- This item must not be sold to any third party vendors.
- 초록/해제
- 요약Deep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans are still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. We study neural networks that have exactly this capability. By employing recurrence, we build neural networks that can expend more computation when needed. Using several datasets designed specifically for studying generalization from easy problems to harder test samples, we show that our recurrent networks can extrapolate from easy training data to much harder examples at test time, and they do so with many more iterations of a recurrent block of layers than are used during training.
- 일반주제명
- Computer science.
- 키워드
- Training
- 기타저자
- University of Maryland, College Park Mathematics
- 기본자료저록
- Dissertations Abstracts International. 84-12B.
- 기본자료저록
- Dissertation Abstract International
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008240612s2023 us |||||||||||||||c||eng d■001000016931747
■00520240214100112
■006m o d
■007cr#unu||||||||
■020 ▼a9798379761950
■035 ▼a(MiAaPQ)AAI30421745
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aSchwarzschild, Avi.▼0(orcid)0000-0003-0997-4867
■24510▼aDeep Thinking Systems: Logical Extrapolation With Recurrent Neural Networks▼h[electronic resource]
■260 ▼a[S.l.]:▼bUniversity of Maryland, College Park. ▼c2023
■260 1▼aAnn Arbor :▼bProQuest Dissertations & Theses, ▼c2023
■300 ▼a1 online resource(124 p.)
■500 ▼aSource: Dissertations Abstracts International, Volume: 84-12, Section: B.
■500 ▼aAdvisor: Goldstein, Tom.
■5021 ▼aThesis (Ph.D.)--University of Maryland, College Park, 2023.
■506 ▼aThis item must not be sold to any third party vendors.
■520 ▼aDeep neural networks are powerful machines for visual pattern recognition, but reasoning tasks that are easy for humans are still be difficult for neural models. Humans possess the ability to extrapolate reasoning strategies learned on simple problems to solve harder examples, often by thinking for longer. We study neural networks that have exactly this capability. By employing recurrence, we build neural networks that can expend more computation when needed. Using several datasets designed specifically for studying generalization from easy problems to harder test samples, we show that our recurrent networks can extrapolate from easy training data to much harder examples at test time, and they do so with many more iterations of a recurrent block of layers than are used during training.
■590 ▼aSchool code: 0117.
■650 4▼aComputer science.
■653 ▼aDeep neural networks
■653 ▼aRecurrent networks
■653 ▼aTraining
■690 ▼a0800
■690 ▼a0984
■71020▼aUniversity of Maryland, College Park▼bMathematics.
■7730 ▼tDissertations Abstracts International▼g84-12B.
■773 ▼tDissertation Abstract International
■790 ▼a0117
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931747▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202402▼f2024
