서브메뉴
검색
Towards Pragmatic Time Series Intelligence
Towards Pragmatic Time Series Intelligence
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103506
- ISBN
- 9798315741725
- DDC
- 629.8
- 서명/저자
- Towards Pragmatic Time Series Intelligence
- 발행사항
- [Sl] : Carnegie Mellon University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 199 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
- 주기사항
- Advisor: Dubrawski, Artur.
- 학위논문주기
- Thesis (Ph.D.)--Carnegie Mellon University, 2025.
- 초록/해제
- 요약This thesis aims to democratize time series intelligence by making advanced modeling capabilities accessible to users without specialized machine learning knowledge. We pursue this goal through three complementary contributions that build foundation models, improve our understanding of them, and address challenges emerging in their practical use. We start by introducing MOMENT, the first family of open source time series foundation models capable of performing well on a variety of tasks on data from diverse domains with minimal supervision. We extend these models to handle long multivariate contexts and integrate multimodal data, enabling their application to complex real-world scenarios where traditional approaches often fall short. Next, we examine what these foundation models learn by investigating their compositional reasoning abilities, representation structures, and encoded concepts. We identify practical insights that improve both our understanding of the models and their performance. Then, we tackle deployment challenges by developing methods to learn from distributed unlabeled data, assess label quality, and select robust models when labeled data is scarce. We conclude this thesis by exploring how Large Language Model agents can automate the time series intelligence engineering process, using open-source tools and tools developed in this thesis. We demonstrate the utility of our methods in clinical settings, where time series data is plentiful and where modeling it can be impactful. We conclude that specialized foundation models, combined with practical tools supporting their real-world deployment, can substantially advance time series intelligence and yield practical solutions of societal importance.
- 일반주제명
- Robotics
- 일반주제명
- Engineering
- 일반주제명
- Information technology
- 키워드
- Generative AI
- 키워드
- Healthcare
- 키워드
- Machine learning
- 키워드
- Multimodality
- 키워드
- Time series
- 기타저자
- Carnegie Mellon University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017357395
■00520260202103506
■006m o d
■007cr#unu||||||||
■020 ▼a9798315741725
■035 ▼a(MiAaPQ)AAI32002632
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a629.8
■1001 ▼aGoswami, Mononito.▼0(orcid)0000-0002-4117-5558
■24510▼aTowards Pragmatic Time Series Intelligence
■260 ▼a[Sl]▼bCarnegie Mellon University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a199 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: B.
■500 ▼aAdvisor: Dubrawski, Artur.
■5021 ▼aThesis (Ph.D.)--Carnegie Mellon University, 2025.
■520 ▼aThis thesis aims to democratize time series intelligence by making advanced modeling capabilities accessible to users without specialized machine learning knowledge. We pursue this goal through three complementary contributions that build foundation models, improve our understanding of them, and address challenges emerging in their practical use. We start by introducing MOMENT, the first family of open source time series foundation models capable of performing well on a variety of tasks on data from diverse domains with minimal supervision. We extend these models to handle long multivariate contexts and integrate multimodal data, enabling their application to complex real-world scenarios where traditional approaches often fall short. Next, we examine what these foundation models learn by investigating their compositional reasoning abilities, representation structures, and encoded concepts. We identify practical insights that improve both our understanding of the models and their performance. Then, we tackle deployment challenges by developing methods to learn from distributed unlabeled data, assess label quality, and select robust models when labeled data is scarce. We conclude this thesis by exploring how Large Language Model agents can automate the time series intelligence engineering process, using open-source tools and tools developed in this thesis. We demonstrate the utility of our methods in clinical settings, where time series data is plentiful and where modeling it can be impactful. We conclude that specialized foundation models, combined with practical tools supporting their real-world deployment, can substantially advance time series intelligence and yield practical solutions of societal importance.
■590 ▼aSchool code: 0041.
■650 4▼aRobotics
■650 4▼aEngineering
■650 4▼aInformation technology
■653 ▼aFoundation models
■653 ▼aGenerative AI
■653 ▼aHealthcare
■653 ▼aMachine learning
■653 ▼aMultimodality
■653 ▼aTime series
■690 ▼a0771
■690 ▼a0489
■690 ▼a0800
■690 ▼a0537
■71020▼aCarnegie Mellon University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-11B.
■790 ▼a0041
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357395▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
