Neural network based on systematically generated smoothing functions for absolute value equation

B. Saheya, Chieu Thanh Nguyen, Jein Shan Chen

研究成果: 雜誌貢獻文章

摘要

In this paper, we summarize several systematic ways of constructing smoothing functions and illustrate eight smoothing functions accordingly. Then, based on these systematically generated smoothing functions, a unified neural network model is proposed for solving absolute value equation. The issues regarding the equilibrium point, the trajectory, and the stability properties of the neural network are addressed. Moreover, numerical experiments with comparison are presented, which suggests what kind of smoothing functions work well along with the neural network approach.

原文英語
頁(從 - 到)533-558
頁數26
期刊Journal of Applied Mathematics and Computing
61
發行號1-2
DOIs
出版狀態已發佈 - 2019 十月 1
對外發佈Yes

ASJC Scopus subject areas

  • Computational Mathematics
  • Applied Mathematics

指紋 深入研究「Neural network based on systematically generated smoothing functions for absolute value equation」主題。共同形成了獨特的指紋。

  • 引用此