Recurrent Neural Networks for Solving Real-Time Linear System of Equations

Conference paper
First Online:
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 690)

Abstract

In this paper, a new recurrent neural network (RNN) model is proposed and investigated for solving real-time linear system of equations. The proposed model has an advantage over the existing RNNs, specifically, the gradient-based neural network, Zhang neural network in terms of convergence performance. In addition, theoretical analysis is given, and illustrative example further demonstrates the effectiveness and efficiency of the presented model for the real-time solution of linear equations.

Keywords

Recurrent neural network Global convergence performance Linear system of equations 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Wang, J.: Electronic realization of recurrent neural work for solving simultaneous linear equations. Electron. Lett. 28(5), 493–495 (1992)CrossRefGoogle Scholar
  2. 2.
    Sturges, R.H.J.: Anolog matrix inversion (robot kinematics). IEEE J. Robot. Autom. 4(2), 157–162 (1988)CrossRefGoogle Scholar
  3. 3.
    Yi, C., Zhang, Y.: Analogue recurrent neural network for linear algebraic equation solving. Electron. Lett. 44(18), 1078–1079 (2008)CrossRefGoogle Scholar
  4. 4.
    Chen, K.: Robustness analysis of Wang neural network for online linear equation solving. Electron. Lett. 48(22), 1391–1392 (2012)CrossRefGoogle Scholar
  5. 5.
    Chen, K.: Implicit dynamic system for online simultaneous linear equations solving. Electron. Lett. 49(2), 101–102 (2013)CrossRefGoogle Scholar
  6. 6.
    Zhang, Y., Ge, S.S.: Design and analysis of a general recurrent neural network model for time-varying matrix inversion. IEEE Trans. Neural Netw. 16(6), 1477–1490 (2005)CrossRefGoogle Scholar
  7. 7.
    Zhang, Y., Wang, J.: Global exponential stability of recurrent neural networks for synthesizing linear feedback control systems via pole assignment. IEEE Trans. Neural Netw. 13(3), 633–644 (2002)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Nanfang College of Sun Yat-Sen UniversityGuangzhouChina
  2. 2.School of Automation Science and EngineeringSouth China University of TechnologyGuangzhouChina
  3. 3.School of Data and Computer ScienceSun Yat-Sen UniversityGuangzhouChina

Personalised recommendations