| 模糊边界训练样本输入网络及其学习能力 |
| |
| 引用本文： | 胡瑞敏,徐正全,彭骏.模糊边界训练样本输入网络及其学习能力[J].华中科技大学学报(自然科学版),1997(Z1). |
| |
| 作者姓名： | 胡瑞敏 徐正全 彭骏 |
| |
| 作者单位： | 香港理工大学，武汉测绘科技大学 |
| |
| 摘 要： | 研究了具有模糊边界样本的网络学习能力，提出了与之相应的ＴｙｐｉｃａｌＩｎｐｕｔＳａｍｐｌｅｓＴｒａｉｎｉｎｇＡｌ－ｇｏｒｉｔｈｍ（ＴＩＳＴＡ）算法并将它与自然时序训练算法进行比较．数学分析和计算机仿真实验结果均证明，ＴＩＳＴＡ算法有效地避免了传统算法的不足，提高了网络的分类性能．
|
| 关 键 词： | 神经网络 预处理 网络学习 模式识别 |
A Study of the Input Network with a Training Sample of Fuzzy Boundary and Its Learning Capability |
| |
| Hu Ruimin Dept. of Electronics & Information Eng.,HUST,Wuhan ,China. Xu Zhengquan Peng Jun Yao Tianren.A Study of the Input Network with a Training Sample of Fuzzy Boundary and Its Learning Capability[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,1997(Z1). |
| |
| Authors: | Hu Ruimin Dept of Electronics & Information Eng HUST Wuhan China Xu Zhengquan Peng Jun Yao Tianren |
| |
| Institution: | Hu Ruimin Dept. of Electronics & Information Eng.,HUST,Wuhan 430074,China. Xu Zhengquan Peng Jun Yao Tianren |
| |
| Abstract: | The learning capability of the network with a sample of fuzzy boundary is studied and a typical input sample training algorithm (TISTA) is proposed. The algorithm proposed is compared with the natural sequential training algorithm. It has been proved by both the results of mathematical analysis and computer simulation experiment that the TISTA can overcome the deficiency of the conventional algorithm and improve the classifying capability of the network. |
| |
| Keywords: | neural network pre processing network learning pattern recognition |
| 本文献已被 CNKI 等数据库收录！ |
