본문

서브메뉴

An Exploration of Advancing Efficiency in Learning-Based Systems
An Exploration of Advancing Efficiency in Learning-Based Systems
An Exploration of Advancing Efficiency in Learning-Based Systems

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105657
ISBN  
9798263307202
DDC  
004
저자명  
Wang, Yite.
서명/저자  
An Exploration of Advancing Efficiency in Learning-Based Systems
발행사항  
[Sl] : University of Illinois at Urbana-Champaign, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
150 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
주기사항  
Advisor: Hovakimyan, Naira.
학위논문주기  
Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2024.
초록/해제  
요약Over the past decade, learning-based systems like deep neural networks (DNNs) have demonstrated remarkable success across a range of applications, such as machine vision, natural language processing, computational physics, and robotics. However, these modern DNNs often have a large number of parameters, leading to high computational demands in both training and deployment. This issue is particularly acute in the context of large-scale models like the generative pretrained transformer, e.g., GPT-3, where training expenses can cost millions of dollars. Moreover, the deployment of these models in resource-constrained environments, such as mobile robotics, drones, and intelligent driving systems, further exacerbates the challenge, hindering the full exploitation of DNNs' potential. In my Ph.D. research, I have dedicated my efforts to addressing these computational burdens, focusing on both the training and inference stages. From large to small. The initial part of my work focuses on developing more efficient neural networks through neural architecture search (NAS) and pruning, tailored to various optimization problems. We start with the application for classical minimization problems, leveraging the Neural Tangent Kernel (NTK) theory in Chapter 3 to introduce a novel pruning-at-initialization method tailored for image classification tasks, thereby optimizing computational efficiency. Progressing to bi-level optimization problem, i.e., meta-learning ('learning to learn'), in chapter 4, we explore NAS to automate the process of finding efficient neural network architecture, based on the theoretical insights provided by the NTK theory. Finally, we study the min-max problem associated with generative adversarial neural networks (GANs) in chapter 5. We investigate pruning-during-training method to reduce both training and inference costs of sparse GANs. From small to large. The latter part of my research focuses on transferring knowledge from small networks to larger networks for efficient training. In chapter 6, we present a novel approach to initialize large neural networks by leveraging pre-trained smaller networks, thereby substantially reducing the computational demands of the training process. The effectiveness of these methodologies is empirically demonstrated across a spectrum of applications. Our proposed methods have shown remarkable performance in tasks such as image generation, classification, and language understanding, setting new benchmarks for computational efficiency. Overall, this body of work not only contributes to the practicality and sustainability of DNNs in resource-constrained scenarios but also hopes to inspire future advancements in the field, paving the way for more efficient and accessible learning-based systems.
일반주제명  
Computer science
일반주제명  
Mechanical engineering
일반주제명  
Computer engineering
키워드  
Efficient learning
키워드  
Optimization
키워드  
Statistical learning
키워드  
Learning-based system
키워드  
Data science
키워드  
Deep learning
기타저자  
University of Illinois at Urbana-Champaign Mechanical Sci & Engineering
기본자료저록  
Dissertations Abstracts International. 87-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2024        us                              c    eng  d
■001000017361048
■00520260202105657
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263307202
■035    ▼a(MiAaPQ)AAI32409799
■035    ▼a(MiAaPQ)124371
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aWang,  Yite.
■24513▼aAn  Exploration  of  Advancing  Efficiency  in  Learning-Based  Systems
■260    ▼a[Sl]▼bUniversity  of  Illinois  at  Urbana-Champaign▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a150  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-05,  Section:  B.
■500    ▼aAdvisor:  Hovakimyan,  Naira.
■5021  ▼aThesis  (Ph.D.)--University  of  Illinois  at  Urbana-Champaign,  2024.
■520    ▼aOver  the  past  decade,  learning-based  systems  like  deep  neural  networks  (DNNs)  have  demonstrated  remarkable  success  across  a  range  of  applications,  such  as  machine  vision,  natural  language  processing,  computational  physics,  and  robotics.  However,  these  modern  DNNs  often  have  a  large  number  of  parameters,  leading  to  high  computational  demands  in  both  training  and  deployment.  This  issue  is  particularly  acute  in  the  context  of  large-scale  models  like  the  generative  pretrained  transformer,  e.g.,  GPT-3,  where  training  expenses  can  cost  millions  of  dollars.  Moreover,  the  deployment  of  these  models  in  resource-constrained  environments,  such  as  mobile  robotics,  drones,  and  intelligent  driving  systems,  further  exacerbates  the  challenge,  hindering  the  full  exploitation  of  DNNs'  potential.                        In  my  Ph.D.  research,  I  have  dedicated  my  efforts  to  addressing  these  computational  burdens,  focusing  on  both  the  training  and  inference  stages.                          From  large  to  small.  The  initial  part  of  my  work  focuses  on  developing  more  efficient  neural  networks  through  neural  architecture  search  (NAS)  and  pruning,  tailored  to  various  optimization  problems.  We  start  with  the  application  for  classical  minimization  problems,  leveraging  the  Neural  Tangent  Kernel  (NTK)  theory  in  Chapter  3  to  introduce  a  novel  pruning-at-initialization  method  tailored  for  image  classification  tasks,  thereby  optimizing  computational  efficiency.  Progressing  to  bi-level  optimization  problem,  i.e.,  meta-learning  ('learning  to  learn'),  in  chapter  4,  we  explore  NAS  to  automate  the  process  of  finding  efficient  neural  network  architecture,  based  on  the  theoretical  insights  provided  by  the  NTK  theory.    Finally,  we  study  the  min-max  problem  associated  with  generative  adversarial  neural  networks  (GANs)  in  chapter  5.  We  investigate  pruning-during-training  method  to  reduce  both  training  and  inference  costs  of  sparse  GANs.                        From  small  to  large.  The  latter  part  of  my  research  focuses  on  transferring  knowledge  from  small  networks  to  larger  networks  for  efficient  training.    In  chapter  6,  we  present  a  novel  approach  to  initialize  large  neural  networks  by  leveraging  pre-trained  smaller  networks,  thereby  substantially  reducing  the  computational  demands  of  the  training  process.                        The  effectiveness  of  these  methodologies  is  empirically  demonstrated  across  a  spectrum  of  applications.  Our  proposed  methods  have  shown  remarkable  performance  in  tasks  such  as  image  generation,  classification,  and  language  understanding,  setting  new  benchmarks  for  computational  efficiency.  Overall,  this  body  of  work  not  only  contributes  to  the  practicality  and  sustainability  of  DNNs  in  resource-constrained  scenarios  but  also  hopes  to  inspire  future  advancements  in  the  field,  paving  the  way  for  more  efficient  and  accessible  learning-based  systems.
■590    ▼aSchool  code:  0090.
■650  4▼aComputer  science
■650  4▼aMechanical  engineering
■650  4▼aComputer  engineering
■653    ▼aEfficient  learning
■653    ▼aOptimization
■653    ▼aStatistical  learning
■653    ▼aLearning-based  system
■653    ▼aData  science
■653    ▼aDeep  learning
■690    ▼a0548
■690    ▼a0984
■690    ▼a0800
■690    ▼a0464
■71020▼aUniversity  of  Illinois  at  Urbana-Champaign▼bMechanical  Sci  &  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g87-05B.
■790    ▼a0090
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17361048▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


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

    ค้นหาข้อมูลรายละเอียด

    • จองห้องพัก
    • ไม่อยู่
    • โฟลเดอร์ของฉัน
    • ขอดูแรก
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    วัสดุ
    Reg No. Call No. ตำแหน่งที่ตั้ง สถานะ ยืมข้อมูล
    TF16526 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * จองมีอยู่ในหนังสือยืม เพื่อให้การสำรองที่นั่งคลิกที่ปุ่มจองห้องพัก

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.