| 基于多项式网络的空袭目标类型识别模型 |
| |
| 引用本文： | 赵丰,郭乃林,陈绍顺.基于多项式网络的空袭目标类型识别模型[J].系统工程与电子技术,2002,24(10):79-82. |
| |
| 作者姓名： | 赵丰 郭乃林 陈绍顺 |
| |
| 作者单位： | 空军工程大学导弹学院指挥工程系,陕西,三原,713800 |
| |
| 摘 要： | 给出了进行目标类型识别的指标集 ,建立了基于多项式前向神经网络识别模型。该模型具有三层结构 ,隐层、输出层分别采用多项式函数和线性函数作为激活函数 ;隐层 输出层的权值用最速下降法学习 ,输入层 隐层的权值用遗传算法进行学习。实例表明该模型是可行的。
|
| 关 键 词： | 目标类型识别 多项式前向神经网络 指标集 |
| 文章编号： | 1001-506X(2002)10-0079-04 |
| 修稿时间： | 2001年7月6日 |
Model of Target Type Recognition Based on Polynomial Neural Networks |
| |
| ZHAO Feng,GUO Nai lin,CHEN Shao shun.Model of Target Type Recognition Based on Polynomial Neural Networks[J].System Engineering and Electronics,2002,24(10):79-82. |
| |
| Authors: | ZHAO Feng GUO Nai lin CHEN Shao shun |
| |
| Abstract: | In this paper,the target type recognition is discussed,index set is given and a model is established by applying polynomial feed forward neural networks. The model has three layers, that is, input layer,hidden layer and output layer.The neural activation functions of the hidden layer and output layer are polynomial function and linear function,respectively.The learning method of hidden output layer weights is the steepest descent method and the one of input hidden layer weights is genetic algorithm.The practical calculation shows that the model is feasible. |
| |
| Keywords: | Target type recognition Polynomial feed forward neural networks Index set |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
