國立高雄大學圖資館 |

登入

回首頁

Integration of Control and Dynamical Systems Perspectives to Machine Learning /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Integration of Control and Dynamical Systems Perspectives to Machine Learning /Motoya Ohnishi.
作者:	Ohnishi, Motoya,
面頁冊數:	1 electronic resource (308 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
附註:	Advisors: Kakade, Sham; Todorov, Emanuel Committee members: Ramos, Fabio.
Contained By:	Dissertations Abstracts International86-01B.
標題:	Computer science.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31240601
ISBN:	9798383227268

Integration of Control and Dynamical Systems Perspectives to Machine Learning /
Ohnishi, Motoya,

Integration of Control and Dynamical Systems Perspectives to Machine Learning /Motoya Ohnishi. - 1 electronic resource (308 pages)

Source: Dissertations Abstracts International, Volume: 86-01, Section: B.

With the increasing demands on artificial intelligence technology operating over sequential data, represented by robotics and language processing, there has been a surge of interest in interdisciplinary research spanning machine learning -- a data-driven approach based on statistics -- and control or dynamical systems theory, which deals with dynamic environments. Because those streams of studies have evolved in a relatively separate manner under different settings and formulations, their integration becomes an intricate task, requiring a fresh look at the existing approach. This thesis primarily revolves around a discussion of research endeavors in the intersection of machine learning and dynamical systems to exploit the best of both worlds, and proposes some of the novel techniques and paradigms made possible by bringing the unique perspectives and concepts from these domains creatively. I initially provide a succinct overview of the state of the art in the related domains followed by my contributions to the fields. First of all, this thesis begins with the work that synthesizes control tools in a learning system to devise algorithms with control theoretic guarantees. In this process, a novel control concept, limited-duration safety, is proposed with discussions on its application within the context of transfer learning. Secondly, a novel model-based reinforcement learning (RL) algorithm is presented, leveraging a recent control theoretic tool as an oracle embedded in the algorithm to provably ensure learning efficiency. With a novel problem formulation with the Koopman operator, which is cast as a generalization of pole assignments to nonlinear decision making, a diverse array of dynamic behaviors are realized. Thirdly, as an additional highlight of exploration, I present the successful extension of RL beyond its conventional reliance on the Bellman equation, encompassing dynamic programming across entire paths. The new framework grounded in theoretical advancements of path signatures has proven beneficial in addressing challenges related to path following. On the other hand, merging machine learning, rooted in statistics, and dynamical systems raises several challenges. In particular, fourthly, this thesis discusses a specific challenge of loss of dynamic structure information that might be caused by concentrations of measures, which is overcome by carefully adopting the asymptotic results of exponential sums. Lastly, a machine learning algorithm itself can be seen as a dynamical system, and this perspective has theoretical and practical potential for handling complex machine learning domains. Especially for a deep RL algorithm, the constructive approach is taken to analyze, in a retroductive manner, the phenomena and performance separations observed in the systems of interest. This thesis is also intended to open a novel direction of further research emerging out of amalgamations of learning algorithms and dynamical systems perspectives, and is concluded with a remark for the potential future work.

English

ISBN: 9798383227268Subjects--Topical Terms:

199325
Computer science.
Subjects--Index Terms:

Control

Integration of Control and Dynamical Systems Perspectives to Machine Learning /
LDR:04581nmm a22004573i 4500 001 676310
005 20250420214340.5
006 m o d
007 cr|nu||||||||
008 250901s2024 miu||||||m |||||||eng d
020 $a 9798383227268
035 $a (MiAaPQD)AAI31240601
035 $a AAI31240601
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Ohnishi, Motoya, $e author. $3 990075
245 1 0 $a Integration of Control and Dynamical Systems Perspectives to Machine Learning / $c Motoya Ohnishi.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (308 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-01, Section: B.
500 $a Advisors: Kakade, Sham; Todorov, Emanuel Committee members: Ramos, Fabio.
502 $b Ph.D. $c University of Washington $d 2024.
520 $a With the increasing demands on artificial intelligence technology operating over sequential data, represented by robotics and language processing, there has been a surge of interest in interdisciplinary research spanning machine learning -- a data-driven approach based on statistics -- and control or dynamical systems theory, which deals with dynamic environments. Because those streams of studies have evolved in a relatively separate manner under different settings and formulations, their integration becomes an intricate task, requiring a fresh look at the existing approach. This thesis primarily revolves around a discussion of research endeavors in the intersection of machine learning and dynamical systems to exploit the best of both worlds, and proposes some of the novel techniques and paradigms made possible by bringing the unique perspectives and concepts from these domains creatively. I initially provide a succinct overview of the state of the art in the related domains followed by my contributions to the fields. First of all, this thesis begins with the work that synthesizes control tools in a learning system to devise algorithms with control theoretic guarantees. In this process, a novel control concept, limited-duration safety, is proposed with discussions on its application within the context of transfer learning. Secondly, a novel model-based reinforcement learning (RL) algorithm is presented, leveraging a recent control theoretic tool as an oracle embedded in the algorithm to provably ensure learning efficiency. With a novel problem formulation with the Koopman operator, which is cast as a generalization of pole assignments to nonlinear decision making, a diverse array of dynamic behaviors are realized. Thirdly, as an additional highlight of exploration, I present the successful extension of RL beyond its conventional reliance on the Bellman equation, encompassing dynamic programming across entire paths. The new framework grounded in theoretical advancements of path signatures has proven beneficial in addressing challenges related to path following. On the other hand, merging machine learning, rooted in statistics, and dynamical systems raises several challenges. In particular, fourthly, this thesis discusses a specific challenge of loss of dynamic structure information that might be caused by concentrations of measures, which is overcome by carefully adopting the asymptotic results of exponential sums. Lastly, a machine learning algorithm itself can be seen as a dynamical system, and this perspective has theoretical and practical potential for handling complex machine learning domains. Especially for a deep RL algorithm, the constructive approach is taken to analyze, in a retroductive manner, the phenomena and performance separations observed in the systems of interest. This thesis is also intended to open a novel direction of further research emerging out of amalgamations of learning algorithms and dynamical systems perspectives, and is concluded with a remark for the potential future work.
546 $a English
590 $a School code: 0250
650 4 $a Computer science. $3 199325
650 4 $a Electrical engineering. $3 454503
650 4 $a Applied mathematics. $3 377601
653 $a Control
653 $a Dynamical systems
653 $a Machine learning
653 $a Robotics
653 $a Reinforcement learning
690 $a 0984
690 $a 0544
690 $a 0364
690 $a 0800
710 2 $a University of Washington. $b Computer Science and Engineering. $3 886663
720 1 $a Kakade, Sham $e degree supervisor.
720 1 $a Todorov, Emanuel $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-01B.
790 $a 0250
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31240601