| 二次最小化问题的有限时间递归神经网络求解 |
| |
| 引用本文： | 张永胜,肖林.二次最小化问题的有限时间递归神经网络求解[J].吉首大学学报(自然科学版),2019,40(2):21-26. |
| |
| 作者姓名： | 张永胜 肖林 |
| |
| 作者单位： | 吉首大学信息科学与工程学院,湖南吉首,416000;吉首大学信息科学与工程学院,湖南吉首,416000 |
| |
| 基金项目： | 国家自然科学基金资助项目（61866013，61503152,61563017,61561022,61363073,61363033）;吉首大学校级科研项目(JDY13) |
| |
| 摘 要： | 利用一类递归神经网络模型来求解二次最小化问题，在该模型的基础上加入双符号幂激励函数，以加快递归神经网络的收敛速度，甚至达到有限时间收敛.通过调节设计参数λ的取值，递归神经网络的收敛性能可进一步提高.利用MATLAB软件对有限递归神经网络模型进行仿真，数值仿真结果验证了模型求解二次最小化问题的有效性和优越性.
|
| 关 键 词： | 二次最小化问题 有限时间 递归神经网络模型 |
Finite-Time Recursive Neural Network for Quadratic Minimization Problems |
| |
| ZHANG Yongsheng,XIAO Lin.Finite-Time Recursive Neural Network for Quadratic Minimization Problems[J].Journal of Jishou University(Natural Science Edition),2019,40(2):21-26. |
| |
| Authors: | ZHANG Yongsheng XIAO Lin |
| |
| Institution: | (School of Information Science and Engineering,Jishou University,Jishou 416000,Hunan China) |
| |
| Abstract: | A recursive neural network model is utilized for solving the quadratic minimization problem,and a sign-bi-power activation function is added to the network model,which speeds up the convergence of the recursive neural network even to reach the finite-time convergence.Moreover,by adjusting the value of the designing parameter λ,the convergence performance of the recursive neural network can be further improved.Finally,the MATLAB is used to simulate and verify the recursive neural network model,and the numerical simulation results verify the effectiveness and superiority of the proposed finite-time recursive neural network model for solving the quadratic minimization problem. |
| |
| Keywords: | quadratic minimization problem finite-time convergence recurrent neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《吉首大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《吉首大学学报(自然科学版)》下载免费的PDF全文 |
