서브메뉴
검색
Neuro-Symbolic Program Synthesis for Data-Efficient Learning
Neuro-Symbolic Program Synthesis for Data-Efficient Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151501
- ISBN
- 9798346807148
- DDC
- 004
- 서명/저자
- Neuro-Symbolic Program Synthesis for Data-Efficient Learning
- 발행사항
- [Sl] : University of California, San Diego, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 203 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-06, Section: B.
- 주기사항
- Advisor: Polikarpova, Nadia.
- 학위논문주기
- Thesis (Ph.D.)--University of California, San Diego, 2024.
- 초록/해제
- 요약The dream of intelligent assistants to enhance programmer productivity has now become a concrete reality, with rapid advances in artificial intelligence. Large language models (LLMs) have demonstrated impressive capabilities in various domains based on the vast amount of data used to train them. However, tasks which require structured reasoning or those underrepresented in their training data continue to be a challenge for LLMs.Program synthesis offers an alternative approach to learning, particularly effective in data-efficient domains with limited training data. It focuses on searching for a program in a domain-specific language that satisfies a given user intent. Program synthesis enables learning of interpretable models that provide correctness and generalizability guarantees from a few data points leading to data-efficient learning. However, purely symbolic methods based on combinatorial search scale poorly to complex problems. To address these challenges, a hybrid paradigm called neurosymbolic synthesis is being explored. This approach integrates the best of both worlds by combining neural networks with symbolic reasoning, thereby enhancing the robustness of AI assistants.This dissertation includes technical contributions spanning symbolic, neurosymbolic and neural approaches to program synthesis. It explores the application of symbolic constraint-based synthesis in SYPHON to model human language, hybrid techniques in PROBE and HYSYNTH that guide symbolic search with a probabilistic model, and neural LLM-driven code generation to automate spreadsheet tasks for end users. Additionally, it focuses on strategies to improve user experience by developing more intuitive and user-friendly programming assistants for the future.
- 일반주제명
- Computer science
- 일반주제명
- Linguistics
- 일반주제명
- Computer engineering
- 키워드
- Neural networks
- 기타저자
- University of California, San Diego Computer Science and Engineering
- 기본자료저록
- Dissertations Abstracts International. 86-06B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161914
■00520250211151501
■006m o d
■007cr#unu||||||||
■020 ▼a9798346807148
■035 ▼a(MiAaPQ)AAI31297918
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aBarke, Shraddha Govind.
■24510▼aNeuro-Symbolic Program Synthesis for Data-Efficient Learning
■260 ▼a[Sl]▼bUniversity of California, San Diego▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a203 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-06, Section: B.
■500 ▼aAdvisor: Polikarpova, Nadia.
■5021 ▼aThesis (Ph.D.)--University of California, San Diego, 2024.
■520 ▼aThe dream of intelligent assistants to enhance programmer productivity has now become a concrete reality, with rapid advances in artificial intelligence. Large language models (LLMs) have demonstrated impressive capabilities in various domains based on the vast amount of data used to train them. However, tasks which require structured reasoning or those underrepresented in their training data continue to be a challenge for LLMs.Program synthesis offers an alternative approach to learning, particularly effective in data-efficient domains with limited training data. It focuses on searching for a program in a domain-specific language that satisfies a given user intent. Program synthesis enables learning of interpretable models that provide correctness and generalizability guarantees from a few data points leading to data-efficient learning. However, purely symbolic methods based on combinatorial search scale poorly to complex problems. To address these challenges, a hybrid paradigm called neurosymbolic synthesis is being explored. This approach integrates the best of both worlds by combining neural networks with symbolic reasoning, thereby enhancing the robustness of AI assistants.This dissertation includes technical contributions spanning symbolic, neurosymbolic and neural approaches to program synthesis. It explores the application of symbolic constraint-based synthesis in SYPHON to model human language, hybrid techniques in PROBE and HYSYNTH that guide symbolic search with a probabilistic model, and neural LLM-driven code generation to automate spreadsheet tasks for end users. Additionally, it focuses on strategies to improve user experience by developing more intuitive and user-friendly programming assistants for the future.
■590 ▼aSchool code: 0033.
■650 4▼aComputer science
■650 4▼aLinguistics
■650 4▼aComputer engineering
■653 ▼aDomain-specific languages
■653 ▼aNeuro-symbolic program
■653 ▼aProgram synthesis
■653 ▼aLarge language models
■653 ▼aNeural networks
■690 ▼a0984
■690 ▼a0290
■690 ▼a0464
■71020▼aUniversity of California, San Diego▼bComputer Science and Engineering.
■7730 ▼tDissertations Abstracts International▼g86-06B.
■790 ▼a0033
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161914▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
