Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/81668
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Mechanical Engineering | - |
dc.creator | Ning, HW | - |
dc.creator | Zhang, JM | - |
dc.creator | Jing, X | - |
dc.creator | Tian, TH | - |
dc.date.accessioned | 2020-02-10T12:28:31Z | - |
dc.date.available | 2020-02-10T12:28:31Z | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | http://hdl.handle.net/10397/81668 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0 | en_US |
dc.rights | The following publication H. Ning, J. Zhang, X. Jing and T. Tian, "Robust Online Learning Method Based on Dynamical Linear Quadratic Regulator," in IEEE Access, vol. 7, pp. 117780-117795, 2019 is available at https://dx.doi.org/10.1109/ACCESS.2019.2936537 | en_US |
dc.subject | Online machine learning | en_US |
dc.subject | Optimal control | en_US |
dc.subject | Linear quadratic regulator | en_US |
dc.subject | Complex noise disturbances | en_US |
dc.title | Robust online learning method based on dynamical linear quadratic regulator | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 117780 | - |
dc.identifier.epage | 117795 | - |
dc.identifier.volume | 7 | - |
dc.identifier.doi | 10.1109/ACCESS.2019.2936537 | - |
dcterms.abstract | In this paper, a novel algorithm is proposed for inferring online learning tasks efficiently. By a carefully designed scheme, the online learning problem is first formulated as a state feedback control problem for a series of finite-dimensional systems. Then, the online linear quadratic regulator (OLQR) learning algorithm is developed to obtain the optimal parameter updating. Solid mathematical analysis on the convergence and rationality of our method is also provided. Compared with the conventional learning methods, our learning framework represents a completely different approach with optimal control techniques, but does not introduce any assumption on the characteristics of noise or learning rate. The proposed method not only guarantees the fast and robust convergence but also achieves better performance in learning efficiency and accuracy, especially for the data streams with complex noise disturbances. In addition, under the proposed framework, new robust algorithms can be potentially developed for various machine learning tasks by using the powerful optimal control techniques. Numerical results on benchmark datasets and practical applications confirm the advantages of our new method. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE access, 2019, v. 7, p. 117780-117795 | - |
dcterms.isPartOf | IEEE access | - |
dcterms.issued | 2019 | - |
dc.identifier.isi | WOS:000484314600001 | - |
dc.description.validate | 202002 bcrc | - |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | OA_Scopus/WOS | en_US |
dc.description.pubStatus | Published | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Ning_Online_Learning_Linear.pdf | 6.25 MB | Adobe PDF | View/Open |
Page views
83
Last Week
2
2
Last month
Citations as of Mar 24, 2024
Downloads
89
Citations as of Mar 24, 2024
SCOPUSTM
Citations
4
Citations as of Mar 29, 2024
WEB OF SCIENCETM
Citations
2
Citations as of Mar 28, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.