본문

서브메뉴

Algorithm-Centric Design of Reliable and Efficient Deep Learning Processing Systems- [electronic resource]
Algorithm-Centric Design of Reliable and Efficient Deep Learning Processing Systems - [ele...
Algorithm-Centric Design of Reliable and Efficient Deep Learning Processing Systems- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100428
ISBN  
9798379759209
DDC  
004
저자명  
Ozen, Elbruz.
서명/저자  
Algorithm-Centric Design of Reliable and Efficient Deep Learning Processing Systems - [electronic resource]
발행사항  
[S.l.]: : University of California, San Diego., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(303 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 84-12, Section: A.
주기사항  
Advisor: Orailoglu, Alex.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Artificial intelligence techniques driven by deep learning have experienced significant advancements in the past decade. The usage of deep learning methods has increased dramatically in practical application domains such as autonomous driving, healthcare, and robotics, where the utmost hardware resource efficiency, as well as strict hardware safety and reliability requirements, are often imposed. The increasing computational cost of deep learning models has been traditionally tackled through model compression and domain-specific accelerator design. As the cost of conventional fault tolerance methods is often prohibitive in consumer electronics, the question of functional safety and reliability for deep learning hardware is still in its infancy. This dissertation outlines a novel approach to deliver dramatic boosts in hardware safety, reliability, and resource efficiency through a synergistic co-design paradigm. We first observe and make use of the unique algorithmic characteristics of deep neural networks, including plasticity in the design process, resiliency to small numerical perturbations, and their inherent redundancy, as well as the unique micro-architectural properties of deep learning accelerators such as regularity. The advocated approach is accomplished by reshaping deep neural networks, enhancing deep neural network accelerators strategically, prioritizing the overall functional correctness, and minimizing the associated costs through the statistical nature of deep neural networks. To illustrate, our analysis demonstrates that deep neural networks equipped with the proposed techniques can maintain accuracy gracefully, even at extreme rates of hardware errors. As a result, the described methodology can embed strong safety and reliability characteristics in mission-critical deep learning applications at a negligible cost. The proposed approach further offers a promising avenue for handling the micro-architectural challenges of deep neural network accelerators and boosting resource efficiency through the synergistic co-design of deep neural networks and hardware micro-architectures.
일반주제명  
Computer science.
일반주제명  
Computer engineering.
일반주제명  
Information science.
키워드  
Deep learning
키워드  
Practical application
키워드  
Hardware
키워드  
Deep neural networks
키워드  
Micro-architectural properties
키워드  
Hardware errors
기타저자  
University of California, San Diego Computer Science and Engineering
기본자료저록  
Dissertations Abstracts International. 84-12A.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016932212
■00520240214100428
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379759209
■035    ▼a(MiAaPQ)AAI30489954
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aOzen,  Elbruz.
■24510▼aAlgorithm-Centric  Design  of  Reliable  and  Efficient  Deep  Learning  Processing  Systems▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  California,  San  Diego.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(303  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  84-12,  Section:  A.
■500    ▼aAdvisor:  Orailoglu,  Alex.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aArtificial  intelligence  techniques  driven  by  deep  learning  have  experienced  significant  advancements  in  the  past  decade.  The  usage  of  deep  learning  methods  has  increased  dramatically  in  practical  application  domains  such  as  autonomous  driving,  healthcare,  and  robotics,  where  the  utmost  hardware  resource  efficiency,  as  well  as  strict  hardware  safety  and  reliability  requirements,  are  often  imposed.  The  increasing  computational  cost  of  deep  learning  models  has  been  traditionally  tackled  through  model  compression  and  domain-specific  accelerator  design.  As  the  cost  of  conventional  fault  tolerance  methods  is  often  prohibitive  in  consumer  electronics,  the  question  of  functional  safety  and  reliability  for  deep  learning  hardware  is  still  in  its  infancy.  This  dissertation  outlines  a  novel  approach  to  deliver  dramatic  boosts  in  hardware  safety,  reliability,  and  resource  efficiency  through  a  synergistic  co-design  paradigm.  We  first  observe  and  make  use  of  the  unique  algorithmic  characteristics  of  deep  neural  networks,  including  plasticity  in  the  design  process,  resiliency  to  small  numerical  perturbations,  and  their  inherent  redundancy,  as  well  as  the  unique  micro-architectural  properties  of  deep  learning  accelerators  such  as  regularity.  The  advocated  approach  is  accomplished  by  reshaping  deep  neural  networks,  enhancing  deep  neural  network  accelerators  strategically,  prioritizing  the  overall  functional  correctness,  and  minimizing  the  associated  costs  through  the  statistical  nature  of  deep  neural  networks.  To  illustrate,  our  analysis  demonstrates  that  deep  neural  networks  equipped  with  the  proposed  techniques  can  maintain  accuracy  gracefully,  even  at  extreme  rates  of  hardware  errors.  As  a  result,  the  described  methodology  can  embed  strong  safety  and  reliability  characteristics  in  mission-critical  deep  learning  applications  at  a  negligible  cost.  The  proposed  approach  further  offers  a  promising  avenue  for  handling  the  micro-architectural  challenges  of  deep  neural  network  accelerators  and  boosting  resource  efficiency  through  the  synergistic  co-design  of  deep  neural  networks  and  hardware  micro-architectures.
■590    ▼aSchool  code:  0033.
■650  4▼aComputer  science.
■650  4▼aComputer  engineering.
■650  4▼aInformation  science.
■653    ▼aDeep  learning
■653    ▼aPractical  application
■653    ▼aHardware
■653    ▼aDeep  neural  networks
■653    ▼aMicro-architectural  properties
■653    ▼aHardware  errors
■690    ▼a0984
■690    ▼a0464
■690    ▼a0723
■71020▼aUniversity  of  California,  San  Diego▼bComputer  Science  and  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g84-12A.
■773    ▼tDissertation  Abstract  International
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16932212▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF08146 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.