Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems

Hyun Ho Kang; Sang Su Lee; Kwan Soo Kim; Choon Ki Ahn

doi:10.1109/SSCI44817.2019.9002701

Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems

Hyun Ho Kang, Sang Su Lee, Kwan Soo Kim, Choon Ki Ahn

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

2 Citations (Scopus)

Abstract

This paper proposes a novel finite memory estimation based learning algorithm (FME-LA) for recurrent neural networks (RNNs) to accurately identify unknown nonlinear systems. The proposed algorithm, FME-LA, is designed through finite memory estimation (FME) whose gain is obtained under the unbiased condition by minimizing the Frobenius norm. The FME is designed on the concept of the horizon to decide how many recent measurements are considered and maintain a finite memory structure of the learning algorithm. Therefore, the proposed algorithm provides accurate performance and fast convergence for the system identification of unknown nonlinear systems under rapidly or smoothly changing circumstances with inaccurate information, such as modeling uncertainties or incorrect noise statistics. We confirm fast convergence and accurate performance of the proposed algorithm through simulation and experimental results.

Original language	English
Title of host publication	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	470-475
Number of pages	6
ISBN (Electronic)	9781728124858
DOIs	https://doi.org/10.1109/SSCI44817.2019.9002701
Publication status	Published - 2019 Dec
Event	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 - Xiamen, China Duration: 2019 Dec 6 → 2019 Dec 9

Publication series

Name	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Conference

Conference	2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019
Country/Territory	China
City	Xiamen
Period	19/12/6 → 19/12/9

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea through the Ministry of Science, ICT, and Future Planning under Grant NRF-2017R1A1A1A05001325, and in part by Human Resources Program in Energy Technology of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No.20174030201820).

Publisher Copyright:
© 2019 IEEE.

Keywords

Finite memory structure
finite memory estimator
learning algorithm
recurrent neural network
unknown nonlinear system identification

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Modelling and Simulation

Access to Document

10.1109/SSCI44817.2019.9002701

Cite this

Kang, H. H., Su Lee, S., Kim, K. S., & Ki Ahn, C. (2019). Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems. In 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 (pp. 470-475). Article 9002701 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI44817.2019.9002701

Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems. / Kang, Hyun Ho; Su Lee, Sang; Kim, Kwan Soo et al.
2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 470-475 9002701 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

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

Kang, HH, Su Lee, S, Kim, KS & Ki Ahn, C 2019, Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems. in 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019., 9002701, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Institute of Electrical and Electronics Engineers Inc., pp. 470-475, 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019, Xiamen, China, 19/12/6. https://doi.org/10.1109/SSCI44817.2019.9002701

Kang HH, Su Lee S, Kim KS, Ki Ahn C. Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems. In 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 470-475. 9002701. (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019). doi: 10.1109/SSCI44817.2019.9002701

Kang, Hyun Ho ; Su Lee, Sang ; Kim, Kwan Soo et al. / Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems. 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 470-475 (2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019).

@inproceedings{95ab7fbcaaff421db8e93385c1f9772a,

title = "Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems",

abstract = "This paper proposes a novel finite memory estimation based learning algorithm (FME-LA) for recurrent neural networks (RNNs) to accurately identify unknown nonlinear systems. The proposed algorithm, FME-LA, is designed through finite memory estimation (FME) whose gain is obtained under the unbiased condition by minimizing the Frobenius norm. The FME is designed on the concept of the horizon to decide how many recent measurements are considered and maintain a finite memory structure of the learning algorithm. Therefore, the proposed algorithm provides accurate performance and fast convergence for the system identification of unknown nonlinear systems under rapidly or smoothly changing circumstances with inaccurate information, such as modeling uncertainties or incorrect noise statistics. We confirm fast convergence and accurate performance of the proposed algorithm through simulation and experimental results.",

keywords = "Finite memory structure, finite memory estimator, learning algorithm, recurrent neural network, unknown nonlinear system identification",

author = "Kang, {Hyun Ho} and {Su Lee}, Sang and Kim, {Kwan Soo} and {Ki Ahn}, Choon",

note = "Funding Information: This work was supported in part by the National Research Foundation of Korea through the Ministry of Science, ICT, and Future Planning under Grant NRF-2017R1A1A1A05001325, and in part by Human Resources Program in Energy Technology of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No.20174030201820). Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019 ; Conference date: 06-12-2019 Through 09-12-2019",

year = "2019",

month = dec,

doi = "10.1109/SSCI44817.2019.9002701",

language = "English",

series = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019",

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

pages = "470--475",

booktitle = "2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019",

}

TY - GEN

T1 - Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems

AU - Kang, Hyun Ho

AU - Su Lee, Sang

AU - Kim, Kwan Soo

AU - Ki Ahn, Choon

N1 - Funding Information: This work was supported in part by the National Research Foundation of Korea through the Ministry of Science, ICT, and Future Planning under Grant NRF-2017R1A1A1A05001325, and in part by Human Resources Program in Energy Technology of the Korea Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No.20174030201820). Publisher Copyright: © 2019 IEEE.

PY - 2019/12

Y1 - 2019/12

N2 - This paper proposes a novel finite memory estimation based learning algorithm (FME-LA) for recurrent neural networks (RNNs) to accurately identify unknown nonlinear systems. The proposed algorithm, FME-LA, is designed through finite memory estimation (FME) whose gain is obtained under the unbiased condition by minimizing the Frobenius norm. The FME is designed on the concept of the horizon to decide how many recent measurements are considered and maintain a finite memory structure of the learning algorithm. Therefore, the proposed algorithm provides accurate performance and fast convergence for the system identification of unknown nonlinear systems under rapidly or smoothly changing circumstances with inaccurate information, such as modeling uncertainties or incorrect noise statistics. We confirm fast convergence and accurate performance of the proposed algorithm through simulation and experimental results.

AB - This paper proposes a novel finite memory estimation based learning algorithm (FME-LA) for recurrent neural networks (RNNs) to accurately identify unknown nonlinear systems. The proposed algorithm, FME-LA, is designed through finite memory estimation (FME) whose gain is obtained under the unbiased condition by minimizing the Frobenius norm. The FME is designed on the concept of the horizon to decide how many recent measurements are considered and maintain a finite memory structure of the learning algorithm. Therefore, the proposed algorithm provides accurate performance and fast convergence for the system identification of unknown nonlinear systems under rapidly or smoothly changing circumstances with inaccurate information, such as modeling uncertainties or incorrect noise statistics. We confirm fast convergence and accurate performance of the proposed algorithm through simulation and experimental results.

KW - Finite memory structure

KW - finite memory estimator

KW - learning algorithm

KW - recurrent neural network

KW - unknown nonlinear system identification

UR - http://www.scopus.com/inward/record.url?scp=85080948815&partnerID=8YFLogxK

U2 - 10.1109/SSCI44817.2019.9002701

DO - 10.1109/SSCI44817.2019.9002701

M3 - Conference contribution

AN - SCOPUS:85080948815

T3 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

SP - 470

EP - 475

BT - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 IEEE Symposium Series on Computational Intelligence, SSCI 2019

Y2 - 6 December 2019 through 9 December 2019

ER -

Finite Memory Estimation-Based Recurrent Neural Network Learning Algorithm for Accurate Identification of Unknown Nonlinear Systems

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this