Open AccessStability analysis of time-varying delay neural network for convex quadratic programming with equality constraints and inequality constraints
Author(s) -
Ling Zhang,
Xiaoqi Sun
Publication year - 2022
Publication title -
discrete and continuous dynamical systems. series b
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.864
H-Index - 53
eISSN - 1553-524X
pISSN - 1531-3492
DOI - 10.3934/dcdsb.2022035
Subject(s) - artificial neural network , uniqueness , quadratic programming , mathematics , quadratic equation , convex optimization , stability (learning theory) , regular polygon , discrete mathematics , computer science , mathematical optimization , artificial intelligence , mathematical analysis , geometry , machine learning
This paper presented a class of neural networks with time-varying delays to solve quadratic programming problems. Compared with previous papers, the neural networks proposed in this paper replaced the constant time delays \begin{document}$ \tau $\end{document} with variable time delays \begin{document}$ \tau(t) $\end{document} and had a more concise structure. There was an improvement of previous method in proving the existence and uniqueness of solutions of the neural networks in this paper. Further, this paper gave the conditions to be satisfied for the global exponential stability of the proposed neural networks. Through numerical examples, this paper verified that the proposed neural networks were accurate and efficient in solving the quadratic programming problems.