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 -