본문

서브메뉴

Training Deep Neural Networks With In-Memory Computing- [electronic resource]
Training Deep Neural Networks With In-Memory Computing - [electronic resource]
Training Deep Neural Networks With In-Memory Computing- [electronic resource]

Detailed Information

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101922
ISBN  
9798380850780
DDC  
621.3
저자명  
Grimm, Christopher L., Jr.
서명/저자  
Training Deep Neural Networks With In-Memory Computing - [electronic resource]
발행사항  
[S.l.]: : Princeton University., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(140 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
주기사항  
Advisor: Verma, Naveen.
학위논문주기  
Thesis (Ph.D.)--Princeton University, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Deep learning has advanced machine capabilities in a variety of fields typically associated with human intelligence, including image recognition, object detection, natural language processing, healthcare, and competitive games. The models behind deep learning called Deep Neural Networks (DNNs) generally require billions of operations for inference, and a hundred if not thousand fold more operations for training. These operations are typically dominated by high dimensionality Matrix-Vector Multiplies (MVMs). Due to the dominance of MVMs, a number of hardware accelerators have been developed to enhance the compute efficiency of MVMs, but data movement and accessing typically remain key bottlenecks. In-Memory Computing (IMC) has the potential to overcome these key bottlenecks by performing computations in-place within dense 2-D memory. However, IMC has challenges of its own, as it fundamentally trades efficiency and throughput gains for dynamic range. This tradeoff is especially challenging for training where higher dynamic range is typically involved in the form of higher compute precision requirements and greater noise sensitivity compared to inferencing. In this work, we will discuss how to enable deep learning training with IMC by mitigating these challenges while substantially mapping operations to IMC. Key advancements in this work include: (1) leveraging new high-precision IMC techniques, like charge-based and analog-input IMC to reduce noise sources; (2) mapping aggressive quantization techniques such as radix-4 gradients to IMC; and (3) ADC range adjustments to better capture output distributions and mitigate biases during training. These methods enable training of DNNs on IMC capable of over 400 x energy savings and of achieving high levels of testing accuracy on a variety of DNN models.
일반주제명  
Computer engineering.
일반주제명  
Electrical engineering.
키워드  
Analog computing
키워드  
Deep learning
키워드  
In-Memory Computing
키워드  
Signal processing
키워드  
Deep Neural Networks
기타저자  
Princeton University Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 85-05B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016935355
■00520240214101922
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380850780
■035    ▼a(MiAaPQ)AAI30691094
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aGrimm,  Christopher  L.,  Jr.
■24510▼aTraining  Deep  Neural  Networks  With  In-Memory  Computing▼h[electronic  resource]
■260    ▼a[S.l.]:▼bPrinceton  University.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(140  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-05,  Section:  B.
■500    ▼aAdvisor:  Verma,  Naveen.
■5021  ▼aThesis  (Ph.D.)--Princeton  University,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aDeep  learning  has  advanced  machine  capabilities  in  a  variety  of  fields  typically  associated  with  human  intelligence,  including  image  recognition,  object  detection,  natural  language  processing,  healthcare,  and  competitive  games.  The  models  behind  deep  learning  called  Deep  Neural  Networks  (DNNs)  generally  require  billions  of  operations  for  inference,  and  a  hundred  if  not  thousand  fold  more  operations  for  training.  These  operations  are  typically  dominated  by  high  dimensionality  Matrix-Vector  Multiplies  (MVMs).  Due  to  the  dominance  of  MVMs,  a  number  of  hardware  accelerators  have  been  developed  to  enhance  the  compute  efficiency  of  MVMs,  but  data  movement  and  accessing  typically  remain  key  bottlenecks.  In-Memory  Computing  (IMC)  has  the  potential  to  overcome  these  key  bottlenecks  by  performing  computations  in-place  within  dense  2-D  memory.  However,  IMC  has  challenges  of  its  own,  as  it  fundamentally  trades  efficiency  and  throughput  gains  for  dynamic  range.  This  tradeoff  is  especially  challenging  for  training  where  higher  dynamic  range  is  typically  involved  in  the  form  of  higher  compute  precision  requirements  and  greater  noise  sensitivity  compared  to  inferencing.  In  this  work,  we  will  discuss  how  to  enable  deep  learning  training  with  IMC  by  mitigating  these  challenges  while  substantially  mapping  operations  to  IMC.  Key  advancements  in  this  work  include:  (1)  leveraging  new  high-precision  IMC  techniques,  like  charge-based  and  analog-input  IMC  to  reduce  noise  sources;  (2)  mapping  aggressive  quantization  techniques  such  as  radix-4  gradients  to  IMC;  and  (3)  ADC  range  adjustments  to  better  capture  output  distributions  and  mitigate  biases  during  training.  These  methods  enable  training  of  DNNs  on  IMC  capable  of  over  400  x  energy  savings  and  of  achieving  high  levels  of  testing  accuracy  on  a  variety  of  DNN  models.
■590    ▼aSchool  code:  0181.
■650  4▼aComputer  engineering.
■650  4▼aElectrical  engineering.
■653    ▼aAnalog  computing
■653    ▼aDeep  learning
■653    ▼aIn-Memory  Computing
■653    ▼aSignal  processing
■653    ▼aDeep  Neural  Networks
■690    ▼a0800
■690    ▼a0464
■690    ▼a0544
■71020▼aPrinceton  University▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-05B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0181
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16935355▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF06276 전자도서 My Folder 부재도서신고 비도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.