Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function

Shuai Li, Sanfeng Chen, Bo Liu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

173 Citations (Scopus)

Abstract

Bartels-Stewart algorithm is an effective and widely used method with an O(n3) time complexity for solving a static Sylvester equation. When applied to time-varying Sylvester equation, the computation burden increases intensively with the decrease of sampling period and cannot satisfy continuous realtime calculation requirements. Gradient-based recurrent neural network are able to solve the time-varying Sylvester equation in real time but there always exists an estimation error. In contrast, the recently proposed Zhang neural network has been proven to converge to the solution of the Sylvester equation ideally when time goes to infinity. However, this neural network with the suggested activation functions never converges to the desired value in finite time, which may limit its applications in realtime processing. To tackle this problem, a sign-bi-power activation function is proposed in this paper to accelerate Zhang neural network to finite-time convergence. The global convergence and finite-time convergence property are proven in theory. The upper bound of the convergence time is derived analytically. Simulations are performed to evaluate the performance of the neural network with the proposed activation function. In addition, the proposed strategy is applied to online calculating the pseudo-inverse of a matrix and nonlinear control of an inverted pendulum system. Both theoretical analysis and numerical simulations validate the effectiveness of proposed activation function.
Original languageEnglish
Pages (from-to)189-205
Number of pages17
JournalNeural Processing Letters
Volume37
Issue number2
DOIs
Publication statusPublished - 1 Apr 2013
Externally publishedYes

Keywords

  • Finite-time convergence
  • Global convergence
  • Sylvester equation
  • Zhang neural network

ASJC Scopus subject areas

  • Software
  • Neuroscience(all)
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this