| 函数连接型神经网络应用于岩石含矿性研究 |
| |
| 引用本文： | 印春生,林腾,于芳,吴孔导,潘忠孝,张懋森,陈江峰. 函数连接型神经网络应用于岩石含矿性研究[J]. 中国科学院研究生院学报, 1999, 0(1) |
| |
| 作者姓名： | 印春生 林腾 于芳 吴孔导 潘忠孝 张懋森 陈江峰 |
| |
| 作者单位： | 中国科学技术大学应用化学系，中国科学技术大学地球与空间科学系 |
| |
| 摘 要： | 函数连接型神经网络是一种无隐含层的新型网络，应用其三阶联合激励增强特性对某矿区矿石与围岩进行判别研究，识别准确率近１００％．在对预测集的每一个输入信号添加２０％的噪音干扰后，发现依然能准确判别．可见网络的容错能力是十分令人满意的．
|
| 关 键 词： | 函数连接型神经网络，联合激励增强，判别，矿石与围岩，容错能力 |
Application of Functional Link Net to Pattern Recognition of Ore and Country Rock |
| |
| Yin Chunsheng Lin Teng Yu Fang Wu Kongdao Pan Zhongxiao Zhang Maosen. Application of Functional Link Net to Pattern Recognition of Ore and Country Rock[J]. Journal of the Graduate School of the Chinese Academy of Sciences, 1999, 0(1) |
| |
| Authors: | Yin Chunsheng Lin Teng Yu Fang Wu Kongdao Pan Zhongxiao Zhang Maosen |
| |
| Abstract: | Functional link net is a novel neural network(FLN),without hidden layer.We use the three order joint activition of FLN to study the pattern recognitions of the ore and country rocks from a mining area.The discrimination is 100%.After adding 20% noise to every input signal of the testing set,the discrimination retains accurate.It is thought that the fault tolerant ability of the FLN is satisfactory. |
| |
| Keywords: | functional link net three order joint activition pattern recognition ore and country rocks fault tolerant ability |
| 本文献已被 CNKI 等数据库收录！ |
