Learning from neural control

Cong Wang; David J. Hill

doi:10.1109/CDC.2003.1271916

Learning from neural control

Cong Wang
, David J. Hill

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

6 Citations (Scopus)

Abstract

One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.

Original language	English
Title of host publication	Proceedings of the IEEE Conference on Decision and Control
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	5721-5726
Number of pages	6
ISBN (Print)	0780379241
DOIs	https://doi.org/10.1109/CDC.2003.1271916
Publication status	Published - 2003
Externally published	Yes
Event	IEEE Conference on Decision and Control 2003 - Maui, United States of America Duration: 9 Dec 2003 → 12 Dec 2003 Conference number: 42nd https://ieeexplore.ieee.org/xpl/conhome/8969/proceeding?isnumber=28478 (Proceedings)

Publication series

Name	Proceedings of the IEEE Conference on Decision and Control
Volume	6
ISSN (Print)	0743-1546
ISSN (Electronic)	2576-2370

Conference

Conference	IEEE Conference on Decision and Control 2003
Abbreviated title	CDC 2003
Country/Territory	United States of America
City	Maui
Period	9/12/03 → 12/12/03
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8969/proceeding?isnumber=28478 (Proceedings)

Access to Document

10.1109/CDC.2003.1271916

Cite this

@inproceedings{eaa7e094eb2e4729b03b01a9bdd0d5e2,

title = "Learning from neural control",

abstract = "One of the amazing successes of biological systems is their ability to {"}learn by doing{"} and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.",

author = "Cong Wang and Hill, \{David J.\}",

year = "2003",

doi = "10.1109/CDC.2003.1271916",

language = "English",

isbn = "0780379241",

series = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "5721--5726",

booktitle = "Proceedings of the IEEE Conference on Decision and Control",

address = "United States of America",

note = "IEEE Conference on Decision and Control 2003, CDC 2003 ; Conference date: 09-12-2003 Through 12-12-2003",

url = "https://ieeexplore.ieee.org/xpl/conhome/8969/proceeding?isnumber=28478",

}

Wang, C & Hill, DJ 2003, Learning from neural control. in Proceedings of the IEEE Conference on Decision and Control. Proceedings of the IEEE Conference on Decision and Control, vol. 6, IEEE, Institute of Electrical and Electronics Engineers, pp. 5721-5726, IEEE Conference on Decision and Control 2003, Maui, Hawaii, United States of America, 9/12/03. https://doi.org/10.1109/CDC.2003.1271916

Learning from neural control. / Wang, Cong; Hill, David J.
Proceedings of the IEEE Conference on Decision and Control. IEEE, Institute of Electrical and Electronics Engineers, 2003. p. 5721-5726 (Proceedings of the IEEE Conference on Decision and Control; Vol. 6).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Learning from neural control

AU - Wang, Cong

AU - Hill, David J.

N1 - Conference code: 42nd

PY - 2003

Y1 - 2003

N2 - One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.

AB - One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, we firstly present an adaptive neural controller which is capable of learning the system dynamics during tracking control to periodic reference orbits. A partial persistent excitation (PE) condition is shown to be satisfied, and accurate NN approximation for the unknown dynamics is obtained in a local region along the tracking orbit. Secondly, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve local stability and better control performance. The significance of this paper is that it presents a dynamical deterministic learning theory, which can implement learning and control abilities similarly to biological systems.

UR - https://www.scopus.com/pages/publications/1542378336

U2 - 10.1109/CDC.2003.1271916

DO - 10.1109/CDC.2003.1271916

M3 - Conference Paper

AN - SCOPUS:1542378336

SN - 0780379241

T3 - Proceedings of the IEEE Conference on Decision and Control

SP - 5721

EP - 5726

BT - Proceedings of the IEEE Conference on Decision and Control

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE Conference on Decision and Control 2003

Y2 - 9 December 2003 through 12 December 2003

ER -

Learning from neural control

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this