서브메뉴
검색
Minimalism Yields Maximum Results: Deep Learning with Limited Resource
Minimalism Yields Maximum Results: Deep Learning with Limited Resource
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152945
- ISBN
- 9798342141505
- DDC
- 300
- 저자명
- Wang, Haoyu.
- 서명/저자
- Minimalism Yields Maximum Results: Deep Learning with Limited Resource
- 발행사항
- [Sl] : Purdue University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 216 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
- 주기사항
- Advisor: Gao, Jing;Su, Lu;Qiu, Qiang;Wang, Xiaoqian;Zhao, Tuo.
- 학위논문주기
- Thesis (Ph.D.)--Purdue University, 2024.
- 초록/해제
- 요약Deep learning models have demonstrated remarkable success across diverse domains, including computer vision and natural language processing. These models heavily rely on resources, encompassing annotated data, computational power, and storage. However, mobile devices, particularly in scenarios like medical or multilingual contexts, often face constraints with computing power, making ample data annotation prohibitively expensive. Developing deep learning models for such resource-constrained scenarios presents a formidable challenge. Our primary goal is to enhance the efficiency of state-of-the-art neural network models tailored for resource-limited scenarios. Our commitment lies in crafting algorithms that not only mitigate annotation requirements but also reduce computational complexity and alleviate storage demands. Our dissertation focuses on two key areas: Parameter-efficient Learning and Data-efficient Learning. In Part 1, we present our studies on parameter-efficient learning. This approach targets the creation of lightweight models for efficient storage or inference. The proposed solutions are tailored for diverse tasks, including text generation, text classification, and text/image retrieval. In Part 2, we showcase our proposed methods for data-efficient learning, concentrating on cross-lingual and multi-lingual text classification applications.
- 일반주제명
- Privacy
- 일반주제명
- Computer science
- 기타저자
- Purdue University.
- 기본자료저록
- Dissertations Abstracts International. 86-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017164300
■00520250211152945
■006m o d
■007cr#unu||||||||
■020 ▼a9798342141505
■035 ▼a(MiAaPQ)AAI31606846
■035 ▼a(MiAaPQ)Purdue26349415
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a300
■1001 ▼aWang, Haoyu.
■24510▼aMinimalism Yields Maximum Results: Deep Learning with Limited Resource
■260 ▼a[Sl]▼bPurdue University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a216 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-05, Section: B.
■500 ▼aAdvisor: Gao, Jing;Su, Lu;Qiu, Qiang;Wang, Xiaoqian;Zhao, Tuo.
■5021 ▼aThesis (Ph.D.)--Purdue University, 2024.
■520 ▼aDeep learning models have demonstrated remarkable success across diverse domains, including computer vision and natural language processing. These models heavily rely on resources, encompassing annotated data, computational power, and storage. However, mobile devices, particularly in scenarios like medical or multilingual contexts, often face constraints with computing power, making ample data annotation prohibitively expensive. Developing deep learning models for such resource-constrained scenarios presents a formidable challenge. Our primary goal is to enhance the efficiency of state-of-the-art neural network models tailored for resource-limited scenarios. Our commitment lies in crafting algorithms that not only mitigate annotation requirements but also reduce computational complexity and alleviate storage demands. Our dissertation focuses on two key areas: Parameter-efficient Learning and Data-efficient Learning. In Part 1, we present our studies on parameter-efficient learning. This approach targets the creation of lightweight models for efficient storage or inference. The proposed solutions are tailored for diverse tasks, including text generation, text classification, and text/image retrieval. In Part 2, we showcase our proposed methods for data-efficient learning, concentrating on cross-lingual and multi-lingual text classification applications.
■590 ▼aSchool code: 0183.
■650 4▼aPrivacy
■650 4▼aComputer science
■690 ▼a0984
■71020▼aPurdue University.
■7730 ▼tDissertations Abstracts International▼g86-05B.
■790 ▼a0183
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164300▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
