| 引用本文: | 石 俊,陈幼平,Peter Wai-tat Tse.前馈网的知识扩充及故障恢复[J].控制理论与应用,2000,17(2):189~192.[点击复制] |
| SHI Jun,CHEN You-ping,Peter Wai-tat Tse.Knowledge Extension and Fault Recovery of Feed Forward Neural Networks[J].Control Theory and Technology,2000,17(2):189~192.[点击复制] |
|
| 前馈网的知识扩充及故障恢复 |
| Knowledge Extension and Fault Recovery of Feed Forward Neural Networks |
| 摘要点击 1814 全文点击 666 投稿时间：1998-05-29 修订日期：1999-03-17 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2000.2.008 |
| 2000,17(2):189-192 |
| 中文关键词 前馈网 学习 故障补偿 |
| 英文关键词 FNN learning fault compensation |
| 基金项目 |
|
| 中文摘要 |
| 针对前馈网扩充性差的问题, 提出了一种知识扩充方法. 在维持原有网络结构不变的基础上, 通过添加一个新的子网, 达到既保存现有训练结果, 又可以学习新知识的目的. 同时, 本文对神经网络的故障恢复策略进行了研究, 提出了相应的补偿算法. 最后通过仿真实验对算法的有效性进行了验证. |
| 英文摘要 |
| Aiming at the problem of poor extensibility of feed forward neural networks,a knowledge extension method is proposed in this paper.Preserving the original neural networks,we can both retain existing training result and learn new knowledge by adding a new subnet.Simultaneously,the strategy of fault recovery of neural networks is studied and a fault compensation algorithm is given.The effectiveness of proposed algorithms is verified by numerical simulations. |
|
|
|
|
|