Journal
NEURAL COMPUTING & APPLICATIONS
Volume 31, Issue -, Pages 793-800Publisher
SPRINGER LONDON LTD
DOI: 10.1007/s00521-017-3010-z
Keywords
Zhang neural networks; Matrix square root; Finite-time convergence; Nonlinear activation function; Upper bound
Categories
Funding
- Natural Science Foundation of Hunan Province, China [2016JJ2101]
- National Natural Science Foundation of China [61563017, 61561022, 61363073, 61363033, 61503152]
- Research Foundation of Education Bureau of Hunan Province, China [15B192]
- Research Foundation of Jishou University, China [2015SYJG034, JGY201643, JG201615]
Ask authors/readers for more resources
In this paper, a finite-time convergent Zhang neural network (ZNN) is proposed and studied for matrix square root finding. Compared to the original ZNN (OZNN) model, the finite-time convergent ZNN (FTCZNN) model fully utilizes a nonlinearly activated sign-bi-power function, and thus possesses faster convergence ability. In addition, the upper bound of convergence time for the FTCZNN model is theoretically derived and estimated by solving differential inequalities. Simulative comparisons are further conducted between the OZNN model and the FTCZNN model under the same conditions. The results validate the effectiveness and superiority of the FTCZNN model for matrix square root finding.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available