| 引用本文: | 李金艳，余英林.二阶神经网络映射能力的研究[J].控制理论与应用,1996,13(4):516~520.[点击复制] |
| LI Jinyan and YU Yinglin.Studies on the Approximation Capability of the Second-order Neural Network[J].Control Theory and Technology,1996,13(4):516~520.[点击复制] |
|
| 二阶神经网络映射能力的研究 |
| Studies on the Approximation Capability of the Second-order Neural Network |
| 摘要点击 912 全文点击 448 投稿时间：1995-01-17 修订日期：1995-11-27 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 |
| 1996,13(4):516-520 |
| 中文关键词 二阶神经网络 逼近 二阶神经网络的BP算法 |
| 英文关键词 second-order neural network approximation BP algorithm for second-order neural network |
| 基金项目 |
|
| 中文摘要 |
| 本文讨论了二阶神经网络的映射能力．主要内容包括：（1）从理论上严格地证明了二阶神经网络能以任意精度逼近任意连续函数．（2）给出了二阶神经网络的BP算法．（3）模拟实验结果．模拟实验表明：在中间隐层单元数目相同的条件下，二阶神经网络的误差函数比一阶神经网络下降得快；在误差精度相同的条件下，二阶神经网络的隐层单元数目远比一阶神经网络少. |
| 英文摘要 |
| The approximation capability of the second-order neural network is investigated in this paper and the following results have been obtained：1）It has been proved that the accuracy；2）the BP algorithm for second-order neural network and the simulated results are given in this paper.The simulated experiments show that when the number of hidden neural network decreases faster than the first-order one，s；when the accuracies of both of the second-order and first-order neural network are equal，the number of hidden neurons in the second-order is far smaller than the first-order one，s. |