Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
11012487 | Neurocomputing | 2018 | 32 Pages |
Abstract
To solve nonlinear and nonconvex optimization problems, a novel finite-time varying-parameter convergent-differential neural network (termed as FT-VP-CDNN) is proposed and analyzed. Compared with finite-time fixed-parameter convergent-differential neural networks (FT-FP-CDNNs), the proposed FT-VP-CDNN has super exponential convergence, finite-time convergence and strong robustness. Finite-time convergence property of the FT-VP-CDNN is proved and various computer simulations are presented. Numerical simulations verify the superiority of the FT-VP-CDNN when solving nonlinear and nonconvex optimization problem.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Zhijun Zhang, Lunan Zheng, Lingao Li, Xiaoyan Deng, Lin Xiao, Guoshun Huang,