Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks

Antonio Moran; Masao Nagai

doi:10.1109/IJCNN48605.2020.9206980

Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks

Antonio Moran, Masao Nagai

Sección de Electricidad y Electrónica

Technology

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

Abstract

This paper proposes incremental deep learning methods for training neural networks to control the response of complex nonlinear dynamic systems. By analyzing the complexity of the task to be fulfilled by the neural network, learning strategies are formulated and implemented in an incremental scheme starting from simple tasks and continuing with increasingly complex tasks. The Dynamic Back Propagation algorithm is used for training the neuro-controller in each step of the incremental learning process, considering the system nonlinear dynamics. The results obtained in the control of highly unstable nonlinear systems, and the positioning control of mobile robots verify the effectiveness of the proposed incremental deep learning strategies.

Original language	English
Title of host publication	2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728169262
DOIs	https://doi.org/10.1109/IJCNN48605.2020.9206980
State	Published - Jul 2020
Event	2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom Duration: 19 Jul 2020 → 24 Jul 2020

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Conference

Conference	2020 International Joint Conference on Neural Networks, IJCNN 2020
Country/Territory	United Kingdom
City	Virtual, Glasgow
Period	19/07/20 → 24/07/20

Keywords

dynamic back propagation
incremental learning
mobile robots
neuro-control
recurrent neural networks

Access to Document

10.1109/IJCNN48605.2020.9206980

Cite this

Moran, A., & Nagai, M. (2020). Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks. In 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings Article 9206980 (Proceedings of the International Joint Conference on Neural Networks). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN48605.2020.9206980

@inproceedings{5a41e5529772478bbd63d70f3d3d0758,

title = "Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks",

abstract = "This paper proposes incremental deep learning methods for training neural networks to control the response of complex nonlinear dynamic systems. By analyzing the complexity of the task to be fulfilled by the neural network, learning strategies are formulated and implemented in an incremental scheme starting from simple tasks and continuing with increasingly complex tasks. The Dynamic Back Propagation algorithm is used for training the neuro-controller in each step of the incremental learning process, considering the system nonlinear dynamics. The results obtained in the control of highly unstable nonlinear systems, and the positioning control of mobile robots verify the effectiveness of the proposed incremental deep learning strategies.",

keywords = "dynamic back propagation, incremental learning, mobile robots, neuro-control, recurrent neural networks",

author = "Antonio Moran and Masao Nagai",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 International Joint Conference on Neural Networks, IJCNN 2020 ; Conference date: 19-07-2020 Through 24-07-2020",

year = "2020",

month = jul,

doi = "10.1109/IJCNN48605.2020.9206980",

language = "English",

series = "Proceedings of the International Joint Conference on Neural Networks",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings",

}

Moran, A & Nagai, M 2020, Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks. in 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings., 9206980, Proceedings of the International Joint Conference on Neural Networks, Institute of Electrical and Electronics Engineers Inc., 2020 International Joint Conference on Neural Networks, IJCNN 2020, Virtual, Glasgow, United Kingdom, 19/07/20. https://doi.org/10.1109/IJCNN48605.2020.9206980

Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks. / Moran, Antonio; Nagai, Masao.
2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9206980 (Proceedings of the International Joint Conference on Neural Networks).

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

TY - GEN

T1 - Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks

AU - Moran, Antonio

AU - Nagai, Masao

PY - 2020/7

Y1 - 2020/7

N2 - This paper proposes incremental deep learning methods for training neural networks to control the response of complex nonlinear dynamic systems. By analyzing the complexity of the task to be fulfilled by the neural network, learning strategies are formulated and implemented in an incremental scheme starting from simple tasks and continuing with increasingly complex tasks. The Dynamic Back Propagation algorithm is used for training the neuro-controller in each step of the incremental learning process, considering the system nonlinear dynamics. The results obtained in the control of highly unstable nonlinear systems, and the positioning control of mobile robots verify the effectiveness of the proposed incremental deep learning strategies.

AB - This paper proposes incremental deep learning methods for training neural networks to control the response of complex nonlinear dynamic systems. By analyzing the complexity of the task to be fulfilled by the neural network, learning strategies are formulated and implemented in an incremental scheme starting from simple tasks and continuing with increasingly complex tasks. The Dynamic Back Propagation algorithm is used for training the neuro-controller in each step of the incremental learning process, considering the system nonlinear dynamics. The results obtained in the control of highly unstable nonlinear systems, and the positioning control of mobile robots verify the effectiveness of the proposed incremental deep learning strategies.

KW - dynamic back propagation

KW - incremental learning

KW - mobile robots

KW - neuro-control

KW - recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85093832738&partnerID=8YFLogxK

U2 - 10.1109/IJCNN48605.2020.9206980

DO - 10.1109/IJCNN48605.2020.9206980

M3 - Conference contribution

AN - SCOPUS:85093832738

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 International Joint Conference on Neural Networks, IJCNN 2020

Y2 - 19 July 2020 through 24 July 2020

ER -

Moran A, Nagai M. Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks. In 2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9206980. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN48605.2020.9206980

Control of Complex Nonlinear Dynamic Systems with Incremental Deep Learning Neural Networks

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this