| 引用本文: | 鲍晓红,贾英民.用神经元网络辨识非线性系统中的网络结构选择*[J].控制理论与应用,1997,14(4):489~494.[点击复制] |
| BAO Xiaohong and JIA Yingmin.Network Structure Selection in Neural Network Based Nonlinear System Identification[J].Control Theory and Technology,1997,14(4):489~494.[点击复制] |
|
| 用神经元网络辨识非线性系统中的网络结构选择* |
| Network Structure Selection in Neural Network Based Nonlinear System Identification |
| 摘要点击 688 全文点击 366 投稿时间：1996-01-02 修订日期：1996-06-27 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 1997,14(4):489-494 |
| 中文关键词 多层前馈网 权值拟熵 权值拟熵 非线性系统辨识 目标函数 |
| 英文关键词 multilayer neural networks pseudo-entropy of weights pseudoprobability of weights nonlinear system |
| 基金项目 |
|
| 中文摘要 |
| 本文定义了神经元网络的权值拟熵，在对多层前馈网训练的常规目标函数中加入权值拟熵作为约束项以改变网络的权值分布从而修定网络结构.将此方法用于一类非线性系统的神经网络辨识中可以优化网络模型输入项数和隐节点数目. |
| 英文摘要 |
| In this paper we define the pseudo-entropy of network weights. By adding it into the normalobjective function we can obtain a rational network structure during training. Put this method into the neuralnetwork based nonlinear system identification we can acquire a proper number of input and hidden neurons. |