|
|||||
|
|
| 一种基于区间优化的神经网络学习算法 | |
| 引用本文： | 薛继伟,李耀辉,陈冬芳.一种基于区间优化的神经网络学习算法[J].计算机工程,2006,32(4):192-193,216. |
| 作者姓名： | 薛继伟 李耀辉 陈冬芳 |
| 作者单位： | 1. 大庆石油学院计算机科学与工程学院,大庆163318;中国科学院成都计算机应用研究所,成都,610041 2. 中国科学院成都计算机应用研究所,成都,610041 3. 大庆石油学院计算机科学与工程学院,大庆163318 |
| 基金项目： | 科技部科研项目;国家自然科学基金 |
| 摘 要： | 神经网络的学习算法通常是采用梯度下降法，此方法容易陷入局部极小而得到次最优解。另外，对于有些应用来说，用于训练网络的样本的输入／输出数据无法精确给出，而只能以一定的范围的形式给出，这就给传统的神经网络带来了困难。该文提出了一种基于区间优化的神经网络学习算法，可以很好地解决上面所提到的传统神经网络学习算法的缺点。 |
| 关 键 词： | 神经网络 学习算法 区间算法 全局优化 |
| 文章编号： | 1000-3428（2006）04-0192-02 |
| 收稿时间： | 2005-02-02 |
| 修稿时间： | 2005-02-02 |
A Neural Network's Learning Algorithm Based on Interval Optimization |
|
| XUE Jiwei,LI Yaohui,CHEN Dongfang.A Neural Network''''s Learning Algorithm Based on Interval Optimization[J].Computer Engineering,2006,32(4):192-193,216. | |
| Authors: | XUE Jiwei LI Yaohui CHEN Dongfang |
| Affiliation: | 1. Computer Science and Engineering College, Daqing Petroleum institute, Daqing 163318; 2. Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610041 |
| Abstract: | Neural networks are usually trained using local gradient-based procedures. Such methods are frequently found sub-optimal solutions being trapped in local minima. In solving some application problems, the input/output data sets used to train a neural network may not be hundred percent precise but within certain range. It is difficult for the traditional neural network to solve such problems. A learning algorithm based on interval optimization is presented in this paper. The above disadvantages of the traditional learning algorithm are settled by using this method. |
| Keywords: | Neural network Learning algorithm Interval arithmetic Global optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |