| 神经网络模式识别系统互连权重二值化研究 |
| |
| 引用本文： | 李豫华 孙颖. 神经网络模式识别系统互连权重二值化研究[J]. 光学学报, 1996, 16(10): 497-1500 |
| |
| 作者姓名： | 李豫华 孙颖 |
| |
| 作者单位： | 南开大学现代光学研究所 |
| |
| 基金项目： | 国家自然科学基金和攀登计划所资助 |
| |
| 摘 要： | 在增量算法的基础上，利用截断方法和蒙塔卡罗算法，对以四类飞行目标旋转投影作为学习样本的级联神经网络互连权重进行了二值优化处理，并用非学习样本进行了容错性检验，计算机木匠虱到了满意的结果。
|
| 关 键 词： | 模式识别系统 神经网络 互连权重 灰度阶 |
| 收稿时间： | 1995-04-27 |
Study on Binary Interconnection Weight ofa Cascaded Neural Network for Pattern Recognition System |
| |
| Li Yuhua Sun Ying Shen Jinyuan Zhang Yanxin. Study on Binary Interconnection Weight ofa Cascaded Neural Network for Pattern Recognition System[J]. Acta Optica Sinica, 1996, 16(10): 497-1500 |
| |
| Authors: | Li Yuhua Sun Ying Shen Jinyuan Zhang Yanxin |
| |
| Abstract: | In this paper, based on the increment algorithm, the clipping learning method and Monto Carlo algorithm were used in optimization of a cascaded neural network. As a result, binary interconnection weights were obtained. The error tolerance of the neural network was tested by non learning sets. Computer simulation indicated that the results were satisfactory. |
| |
| Keywords: | pattern recognition system interconnection weight gray levels binary. |
| 本文献已被 CNKI 维普 等数据库收录！ |
