| 三维转动神经网络的研究（2）存贮容量 |
| |
| 引用本文： | 陈振湘 帅建伟. 三维转动神经网络的研究（2）存贮容量[J]. 厦门大学学报(自然科学版), 1996, 35(6): 862-866 |
| |
| 作者姓名： | 陈振湘 帅建伟 |
| |
| 作者单位： | 高技术探索资助 |
| |
| 摘 要： | 在绝热近似基础上，应用信噪比理论分析了网络的存贮容量．当神经元的旋转角态数和方向角态数都很大时，存储容量与神经元的旋转角态数的平方成反比，和方向角态数成正比．当神经元态数较小时，结果趋于Ｈｏｐｆｉｅｌｄ神经网络的存储容量．
|
| 关 键 词： | 神经网络，三维转动，图象识别，存贮容量 |
A Study of the Three-dimensional Rotation Neural Network(2 ) Storage Capacity |
| |
| Chen Zhenxiang, Shuai Jianwei, Zheng Jincheng, Liu Ruitang. A Study of the Three-dimensional Rotation Neural Network(2 ) Storage Capacity[J]. Journal of Xiamen University(Natural Science), 1996, 35(6): 862-866 |
| |
| Authors: | Chen Zhenxiang Shuai Jianwei Zheng Jincheng Liu Ruitang |
| |
| Affiliation: | Dept. of Phys. |
| |
| Abstract: | By using the theory of adiabatic approximation, the storage capacity of the three-dimensional rotation neural network is estimated by the signal-to-noise theory. The storage capacity is proportional inversely to the square of the rotation angles states and to the direction angles states of neurons when the neuron states is very big, and approaches to that of the Hopfield model when the neuron states is small. |
| |
| Keywords: | Neural network Three-dimension rotation Pattern recognition storage capacity |
| 本文献已被 CNKI 维普 等数据库收录！ |
