서브메뉴
검색
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
- Optimization
- 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
ค้นหาข้อมูลรายละเอียด
- จองห้องพัก
- ไม่อยู่
- โฟลเดอร์ของฉัน
- ขอดูแรก
- Non-Book Loan Application
- Nighttime Book Loan Application
Available after logging in.


