| 解最小一乘问题的递归神经网络 |
| |
| 引用本文： | 李智勇. 解最小一乘问题的递归神经网络[J]. 集美大学学报(自然科学版), 2015, 0(5): 392-395 |
| |
| 作者姓名： | 李智勇 |
| |
| 作者单位： | （集美大学理学院，福建 厦门 361021） |
| |
| 摘 要： | 应用鞍点理论和投影算子的性质,给出了一种递归神经网络求解具有线性约束的最小一乘问题，证明了此神经网络全局收敛于一个最优解.数值实验表明，用本文的方法求解最小一乘问题是切实可行的.
|
| 关 键 词： | 递归神经网络 最小一乘问题 线性约束 |
A Recurrent Neural Network for Solving Least Absolute Deviation Problem |
| |
| LI Zhi-yong. A Recurrent Neural Network for Solving Least Absolute Deviation Problem[J]. the Editorial Board of Jimei University(Natural Science), 2015, 0(5): 392-395 |
| |
| Authors: | LI Zhi-yong |
| |
| Affiliation: | (School of Science，Jimei University，Xiamen 361021，China) |
| |
| Abstract: | By using the saddle theorem and the properties of projection mapping,a recurrent neural network is proposed for solving least absolute deviation with linear constraints.It is shown that the proposed neural network is globally convergent to an optimal solution.The example given in the paper demonstrates that the proposed approach provides a promising alternative for solving least absolute deviation problem. |
| |
| Keywords: | recurrent neural network least absolute deviation problem linear constraints |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《集美大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《集美大学学报(自然科学版)》下载免费的PDF全文 |
