서브메뉴
검색
Towards Causally-Aware Dynamical System Prediction.
Towards Causally-Aware Dynamical System Prediction.
상세정보
- 자료유형
- 학위논문
- Control Number
- 0017161961
- International Standard Book Number
- 9798382762388
- Dewey Decimal Classification Number
- 004
- Main Entry-Personal Name
- Jiang, Song.
- Publication, Distribution, etc. (Imprint
- [S.l.] : University of California, Los Angeles., 2024
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- Physical Description
- 134 p.
- General Note
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- General Note
- Advisor: Sun, Yizhou.
- Dissertation Note
- Thesis (Ph.D.)--University of California, Los Angeles, 2024.
- Summary, Etc.
- 요약Understanding and predicting the dynamics is one fundamental problem that supports various real-world applications. Deep learning dynamical models such as recurrent neural networks (RNNs) and Transformer show powerful expressiveness in modeling sequential data. However, pure deep learning models lack appropriate inductive bias for dynamics, which limits their potential for more accurate dynamic predictions.This dissertation aims to enhance deep neural networks' capability of modeling dynamics. My research starts by injecting physical law as prior knowledge into deep nets, with the finding that such prior knowledge shapes the predicted trajectory desirably and therefore achieves more accurate forecasting. However, such physical law is not available for more general and complicated dynamics, such as retail time series, and energy consumption sequence. To this end, we propose to use the Fourier series instead of task-specific rules as a more general inductive bias to capture the periodicity. Unfortunately, either specific physical law or general periodic series still just learns the association between historical observations and the future series. However, answering counterfactual questions like "Would the community protection be better had a different group of people gotten vaccinated first?" is one key problem for decision-making in dynamical systems. A dynamical is naturally represented by a graph, where units are nodes and the interactions among them are edges. The second part of my research focuses on how to answer causal questions on graphs and then extend to general dynamical systems.
- Subject Added Entry-Topical Term
- Computer science.
- Subject Added Entry-Topical Term
- Engineering.
- Subject Added Entry-Topical Term
- Information technology.
- Index Term-Uncontrolled
- Deep learning
- Index Term-Uncontrolled
- Recurrent neural networks
- Index Term-Uncontrolled
- Dynamical systems
- Index Term-Uncontrolled
- Sequential data
- Index Term-Uncontrolled
- Deep neural networks
- Added Entry-Corporate Name
- University of California, Los Angeles Computer Science 0201
- Host Item Entry
- Dissertations Abstracts International. 85-11B.
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:656086
MARC
008250224s2024 us ||||||||||||||c||eng d■001000017161961
■00520250211151508
■006m o d
■007cr#unu||||||||
■020 ▼a9798382762388
■035 ▼a(MiAaPQ)AAI31299308
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aJiang, Song.
■24510▼aTowards Causally-Aware Dynamical System Prediction.
■260 ▼a[S.l.]▼bUniversity of California, Los Angeles. ▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a134 p.
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Sun, Yizhou.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2024.
■520 ▼aUnderstanding and predicting the dynamics is one fundamental problem that supports various real-world applications. Deep learning dynamical models such as recurrent neural networks (RNNs) and Transformer show powerful expressiveness in modeling sequential data. However, pure deep learning models lack appropriate inductive bias for dynamics, which limits their potential for more accurate dynamic predictions.This dissertation aims to enhance deep neural networks' capability of modeling dynamics. My research starts by injecting physical law as prior knowledge into deep nets, with the finding that such prior knowledge shapes the predicted trajectory desirably and therefore achieves more accurate forecasting. However, such physical law is not available for more general and complicated dynamics, such as retail time series, and energy consumption sequence. To this end, we propose to use the Fourier series instead of task-specific rules as a more general inductive bias to capture the periodicity. Unfortunately, either specific physical law or general periodic series still just learns the association between historical observations and the future series. However, answering counterfactual questions like "Would the community protection be better had a different group of people gotten vaccinated first?" is one key problem for decision-making in dynamical systems. A dynamical is naturally represented by a graph, where units are nodes and the interactions among them are edges. The second part of my research focuses on how to answer causal questions on graphs and then extend to general dynamical systems.
■590 ▼aSchool code: 0031.
■650 4▼aComputer science.
■650 4▼aEngineering.
■650 4▼aInformation technology.
■653 ▼aDeep learning
■653 ▼aRecurrent neural networks
■653 ▼aDynamical systems
■653 ▼aSequential data
■653 ▼aDeep neural networks
■690 ▼a0984
■690 ▼a0489
■690 ▼a0800
■690 ▼a0537
■71020▼aUniversity of California, Los Angeles▼bComputer Science 0201.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161961▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.