| 一种新的神经网络重新学习算法 |
| |
| 引用本文： | 刘丙杰,胡昌华,马瑞萍.一种新的神经网络重新学习算法[J].系统工程与电子技术,2005,27(1):131-133. |
| |
| 作者姓名： | 刘丙杰 胡昌华 马瑞萍 |
| |
| 作者单位： | 西安第二炮兵工程学院302教研室,陕西,西安,710025 |
| |
| 摘 要： | 训练样本的获取是神经网络应用中的一个"瓶颈"问题。当发现新的训练样本模式时,现有方法就要重新构造新的神经网络、重新训练,学习时间长而且影响原有记忆。为解决此问题,提出了一种新方法,其基本思想是在原有网络的基础上,增加新的局部神经网络,新网络与原有网络没有链接关系,只包含新的样本模式,而且神经网络重新学习时,只调整局部神经网络。
|
| 关 键 词： | 神经网络 训练样本 重新学习 |
| 文章编号： | 1001-506X(2005)01-0131-03 |
| 修稿时间： | 2003年11月4日 |
Novel relearning algorithm of neural network |
| |
| LIU Bing-jie,HU Chang-hua,MA Rui-ping.Novel relearning algorithm of neural network[J].System Engineering and Electronics,2005,27(1):131-133. |
| |
| Authors: | LIU Bing-jie HU Chang-hua MA Rui-ping |
| |
| Abstract: | Obtaining training specimen is a bottleneck in the application of NN. The existing method, which is to rebuild and retrain NN when a new training specimen appears, has two weaknesses: (1) the time of training is increased; (2) old memory is affected. A new method is proposed that a local NN is added based on the eriginal NN. This local NN only includes new specimen mode and is isolated with the original NN. Only local NN is trained when the NN is relearning. |
| |
| Keywords: | neural network training specimen relearn |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
