Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/75469
Title: Rnn models for dynamic matrix inversion : a control-theoretical perspective
Authors: Jin, L 
Li, S 
Hu, B
Keywords: Control-theoretic approach
Dynamic problems with time-varying parameters
Tecurrent neural network (RNN)
Zero-finding methods
Issue Date: 2018
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE transactions on industrial informatics, 2018, v. 14, no. 1, 7953552, p. 189-199 How to cite?
Journal: IEEE transactions on industrial informatics 
Abstract: In this paper, the existing recurrent neural network (RNN) models for solving zero-finding (e.g., matrix inversion) with time-varying parameters are revisited from the perspective of control and unified into a control-theoretical framework. Then, limitations on the activated functions of existing RNN models are pointed out and remedied with the aid of control-theoretical techniques. In addition, gradient-based RNNs, as the classical method for zero-finding, have been remolded to solve dynamic problems in manners free of errors and matrix inversions. Finally, computer simulations are conducted and analyzed to illustrate the efficacy and superiority of the modified RNN models designed from the perspective of control. The main contribution of this paper lies in the removal of the convex restriction and the elimination of the matrix inversion in existing RNN models for the dynamic matrix inversion. This work provides a systematic approach on exploiting control techniques to design RNN models for robustly and accurately solving algebraic equations.
URI: http://hdl.handle.net/10397/75469
ISSN: 1551-3203
EISSN: 1941-0050
DOI: 10.1109/TII.2017.2717079
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

3
Last Week
0
Last month
Citations as of May 13, 2018

WEB OF SCIENCETM
Citations

6
Last Week
0
Last month
Citations as of May 14, 2018

Page view(s)

5
Citations as of May 14, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.