A new finite-time varying-parameter convergent-differential neural-network for solving nonlinear and nonconvex optimization problems

作者：Zhang, Zhijun^*; Zheng, Lunan; Li, Lingao; Deng, Xiaoyan; Xiao, Lin; Huang, Guoshun

来源：Neurocomputing, 2018, 319: 74-83.

DOI：10.1016/j.neucom.2018.07.005

• Nonconvex optimization
• Neural networks
• Nonlinear constraints
• Computer simulations
• Convergence and robustness

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.

• 出版日期2018-11-30
• 单位吉首大学; 佛山科学技术学院; 华南理工大学