Adaptive Coefficient Designs for Nonlinear Activation Function and Its Application to Zeroing Neural Network for Solving Time-Varying Sylvester Equation. Issue 14 (September 2020)

• Record Type: Journal Article
• Authors: Jian, Zhen; Xiao, Lin; Li, Kenli; Zuo, Qiuyue; Zhang, Yongsheng
• Is Part Of: Journal of the Franklin Institute. Volume 357:Issue 14(2020)
• Page Start: 9909
• Page End: 9929
• Publication Date: 2020-09
• Subjects: Science -- Periodicals; Technology -- Periodicals; Patents -- United States -- Periodicals; 505
• DOI: 10.1016/j.jfranklin.2020.06.029
• Languages: English
• ISSNs: 0016-0032

Abstract

Abstract: For obtaining better convergence performance when zeroing neural network (ZNN) is applied to solve time-varying Sylvester equation, three different types of adaptive design coefficients for the sign-bi-power nonlinear activation function are developed and investigated in this paper. Based on these adaptive coefficients, three new adaptive ZNN models are proposed to improve the convergence performance of the standard ZNN model. For better analysis, the effect of two parts constituting the sign-bi-power activation function on the convergence of the standard ZNN model is first discussed. Then, detailed theoretical derivations and proofs are provided to verify excellent performance of the proposed adaptive ZNN models. Finally, illustrative comparison experiments are presented to show the enhanced finite-time convergence performance of the proposed adaptive ZNN models for solving time-varying Sylvester equation.