| 引用本文: | 李 杰,韩正之.一种估计人工神经网络泛化误差的新方法[J].控制理论与应用,2001,18(2):257~259.[点击复制] |
| LI Jie,HAN Zheng-zhi.A New Method to Estimate the Generalization Error of Artificial Neural Network[J].Control Theory and Technology,2001,18(2):257~259.[点击复制] |
|
| 一种估计人工神经网络泛化误差的新方法 |
| A New Method to Estimate the Generalization Error of Artificial Neural Network |
| 摘要点击 1635 全文点击 1008 投稿时间：1998-12-28 修订日期：2000-01-10 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 2001,18(2):257-259 |
| 中文关键词 人工神经网络 泛化误差 结构学习 随机点集 |
| 英文关键词 aritificial neural network generalization constructional learning stochastic set |
| 基金项目 国家自然科学基金(69874025)的资助. |
|
| 中文摘要 |
| 神经网络的结构学习就是要确定网络的拓扑, 使之有较好的泛化能力. 本文考虑了确定性前向网络, 而其训练集合是随机点集的结构学习问题. 文章定义了一种新的结构学习目标函数, 给出了它与目前常用的目标函数比较的优越性, 讨论了相关的学习算法, 还给出了一个例子说明这种学习的效果. |
| 英文摘要 |
| The constructional learning is used to determine the architecture of neural network such that the network holds a satisfactory generalization. This paper considers the constructional learning in the case where the training set is randomly chosen from an input output space. A new objective function of constructional learning is presented. It is illustrated the reason why this objective function is superior to other functions. The learning algorithm for this objective function is also analyzed. Finally, a simulation example is given to show the efficiency of the method presented in this paper. |