소장자료
LDR | 02447cam a2200000 a | ||
001 | 0100563573▲ | ||
005 | 20221018164409▲ | ||
007 | ta ▲ | ||
008 | 211215s2022 nyu b 001 0 eng c▲ | ||
010 | ▼a 2021060635▲ | ||
020 | ▼a9781316519332 (hbk.)▲ | ||
020 | ▼z9781009023405 (epub)▲ | ||
035 | ▼a(KERIS)REF000019817575▲ | ||
040 | ▼aDLC▼beng▼cDLC▼d221016▲ | ||
042 | ▼apcc▲ | ||
050 | 0 | 0 | ▼aQ325.73▼b.R63 2022▲ |
082 | 0 | 4 | ▼a006.3/1▼223/eng20220215▲ |
090 | ▼a006.31▼bR643p▲ | ||
100 | 1 | ▼aRoberts, Daniel A.,▼d1987-▲ | |
245 | 1 | 4 | ▼aThe principles of deep learning theory :▼ban effective theory approach to understanding neural networks /▼cDaniel A. Roberts and Sho Yaida based on research in collaboration with Boris Hanin.▲ |
260 | ▼aNew York :▼bCambridge University Press,▼c2022.▲ | ||
300 | ▼ax, 460 p. ;▼c27 cm▲ | ||
504 | ▼aIncludes bibliographical references and index.▲ | ||
520 | ▼a"This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning"--▼cProvided by publisher.▲ | ||
650 | 0 | ▼aDeep learning (Machine learning)▲ | |
700 | 1 | ▼aYaida, Sho.▲ | |
700 | 1 | ▼aHanin, Boris.▲ |
The principles of deep learning theory : an effective theory approach to understanding neural networks
자료유형
국외단행본
서명/책임사항
The principles of deep learning theory : an effective theory approach to understanding neural networks / Daniel A. Roberts and Sho Yaida based on research in collaboration with Boris Hanin.
발행사항
New York : Cambridge University Press , 2022.
형태사항
x, 460 p. ; 27 cm
서지주기
Includes bibliographical references and index.
요약주기
"This textbook establishes a theoretical framework for understanding deep learning models of practical relevance. With an approach that borrows from theoretical physics, Roberts and Yaida provide clear and pedagogical explanations of how realistic deep neural networks actually work. To make results from the theoretical forefront accessible, the authors eschew the subject's traditional emphasis on intimidating formality without sacrificing accuracy. Straightforward and approachable, this volume balances detailed first-principle derivations of novel results with insight and intuition for theorists and practitioners alike. This self-contained textbook is ideal for students and researchers interested in artificial intelligence with minimal prerequisites of linear algebra, calculus, and informal probability theory, and it can easily fill a semester-long course on deep learning theory. For the first time, the exciting practical advances in modern artificial intelligence capabilities can be matched with a set of effective principles, providing a timeless blueprint for theoretical research in deep learning"-- Provided by publisher.
ISBN
9781316519332 (hbk.)
청구기호
006.31 R643p
소장정보
예도서예약
서서가에없는책 신고
보보존서고신청
캠캠퍼스대출
우우선정리신청
배자료배달신청
문문자발송
출청구기호출력
학소장학술지 원문서비스
등록번호 | 청구기호 | 소장처 | 도서상태 | 반납예정일 | 서비스 |
---|
북토크
자유롭게 책을 읽고
느낀점을 적어주세요
글쓰기
느낀점을 적어주세요
청구기호 브라우징
관련 인기대출 도서