RNN Models for Dynamic Matrix Inversion: A Control-Theoretical Perspective

Long Jin, Shuai Li, Bin Hu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

104 Citations (Scopus)

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.

Original languageEnglish
Article number7953552
Pages (from-to)189-199
Number of pages11
JournalIEEE Transactions on Industrial Informatics
Volume14
Issue number1
DOIs
Publication statusPublished - 1 Jan 2018

Keywords

  • Control-theoretic approach
  • dynamic problems with time-varying parameters
  • recurrent neural network (RNN)
  • zero-finding methods

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this