소장자료
LDR | 02895nam 2200469 4500 | ||
001 | 0100802455▲ | ||
005 | 20240329130945▲ | ||
006 | m o d ▲ | ||
007 | cr#unu||||||||▲ | ||
008 | 240116s2023 us |||||||||||||||c||eng d▲ | ||
020 | ▼a9798380102988▲ | ||
035 | ▼a(MiAaPQ)AAI30572119▲ | ||
040 | ▼aMiAaPQ▼cMiAaPQ▲ | ||
082 | 0 | ▼a616▲ | |
100 | 1 | ▼aGaudio, Alex.▼0(orcid)0000-0003-1380-6620▲ | |
245 | 1 | 0 | ▼aExplainable Deep Machine Learning for Medical Image Analysis▼h[electronic resource]▲ |
260 | ▼a[S.l.]: ▼bCarnegie Mellon University. ▼c2023▲ | ||
260 | 1 | ▼aAnn Arbor : ▼bProQuest Dissertations & Theses, ▼c2023▲ | |
300 | ▼a1 online resource(221 p.)▲ | ||
500 | ▼aSource: Dissertations Abstracts International, Volume: 85-02, Section: B.▲ | ||
500 | ▼aAdvisor: Smailagic, Asim;Campilho, Aurelio.▲ | ||
502 | 1 | ▼aThesis (Ph.D.)--Carnegie Mellon University, 2023.▲ | |
506 | ▼aThis item must not be sold to any third party vendors.▲ | ||
520 | ▼aExplanations justify the development and adoption of algorithmic solutions for prediction problems in medical image analysis. This thesis introduces two guiding principles for creating and exploiting explanations of deep networks and medical image data. The first guiding principle is to use explanations to expose inefficiencies in the design of models and image datasets. The second principle is to leverage tools of compression and fixed-weight methods that minimize learning to make more efficient and effective models and more usable medical image datasets. The outcome is more effective deep learning in medical image analysis. Application of these guiding principles in different settings results in five main contributions: (a) improved understanding of biases present in deep networks and medical images, (b) improved predictive and computational performance of predictive models, (c) creation of ante-hoc models that are interpretable by design, (d) creation of smaller image datasets, and (e) improved visual privacy. This thesis falls within the scope of the TAMI project for Transparent Artificial Machine Intelligence and focuses on explainable artificial intelligence (XAI) for medical image data.▲ | ||
590 | ▼aSchool code: 0041.▲ | ||
650 | 4 | ▼aMedical imaging.▲ | |
653 | ▼aMachine learning▲ | ||
653 | ▼aExploiting explanations▲ | ||
653 | ▼aImage datasets▲ | ||
653 | ▼aDeep networks▲ | ||
653 | ▼aFixed-weight methods▲ | ||
690 | ▼a0800▲ | ||
690 | ▼a0574▲ | ||
710 | 2 | 0 | ▼aCarnegie Mellon University.▼bElectrical and Computer Engineering.▲ |
773 | 0 | ▼tDissertations Abstracts International▼g85-02B.▲ | |
773 | ▼tDissertation Abstract International▲ | ||
790 | ▼a0041▲ | ||
791 | ▼aPh.D.▲ | ||
792 | ▼a2023▲ | ||
793 | ▼aEnglish▲ | ||
856 | 4 | 0 | ▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934151▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.▲ |
Explainable Deep Machine Learning for Medical Image Analysis[electronic resource]
자료유형
국외eBook
서명/책임사항
Explainable Deep Machine Learning for Medical Image Analysis [electronic resource]
개인저자
발행사항
[S.l.] : Carnegie Mellon University. 2023 Ann Arbor : ProQuest Dissertations & Theses , 2023
형태사항
1 online resource(221 p.)
일반주기
Source: Dissertations Abstracts International, Volume: 85-02, Section: B.
Advisor: Smailagic, Asim;Campilho, Aurelio.
Advisor: Smailagic, Asim;Campilho, Aurelio.
학위논문주기
Thesis (Ph.D.)--Carnegie Mellon University, 2023.
요약주기
Explanations justify the development and adoption of algorithmic solutions for prediction problems in medical image analysis. This thesis introduces two guiding principles for creating and exploiting explanations of deep networks and medical image data. The first guiding principle is to use explanations to expose inefficiencies in the design of models and image datasets. The second principle is to leverage tools of compression and fixed-weight methods that minimize learning to make more efficient and effective models and more usable medical image datasets. The outcome is more effective deep learning in medical image analysis. Application of these guiding principles in different settings results in five main contributions: (a) improved understanding of biases present in deep networks and medical images, (b) improved predictive and computational performance of predictive models, (c) creation of ante-hoc models that are interpretable by design, (d) creation of smaller image datasets, and (e) improved visual privacy. This thesis falls within the scope of the TAMI project for Transparent Artificial Machine Intelligence and focuses on explainable artificial intelligence (XAI) for medical image data.
주제
ISBN
9798380102988
관련 인기대출 도서