| 三维转动神经网络的研究：（1）能量函数 |
| |
| 引用本文： | 陈振湘,师建伟.三维转动神经网络的研究：（1）能量函数[J].厦门大学学报(自然科学版),1996,35(3):343-347. |
| |
| 作者姓名： | 陈振湘 师建伟 |
| |
| 基金项目： | 国家自然科学基金,高技术探索资助 |
| |
| 摘 要： | 简述了三维转动神经网络模型，通过对能量函数的研究，证明了网络当神经元个数远大于存贮图象数时，存贮图象为能量空间中的极小值．引入了绝热近似，有效局域场能正确迭代的几率，等于方向角和旋转角分别能正确选代的几率的乘积．
|
| 关 键 词： | 神经网络，三维转动，存贮容量 |
A Study of the Three-dimensional-rotational Neural Networks (1)Energy Function |
| |
| Chen Zhenxiang, Shuai Jianwei,Zheng Jincheng,Liu Ruitang.A Study of the Three-dimensional-rotational Neural Networks (1)Energy Function[J].Journal of Xiamen University(Natural Science),1996,35(3):343-347. |
| |
| Authors: | Chen Zhenxiang Shuai Jianwei Zheng Jincheng Liu Ruitang |
| |
| Institution: | Dept. of Phys. |
| |
| Abstract: | After simply introducing the three-dimensional-rotational neural networks model, the energy function is studied. The energies of the stored patterns are minima in the casethe neurons number is much more larger than that of the stored patterns. With the adiabatic approximation, the probability of correct retrieval of the local field is equal to the multiplication of the probabilities of correct retrieval of the direction angle and the rotation angles. |
| |
| Keywords: | Neural network Three-dimensional rotation storage capacity |
| 本文献已被 CNKI 维普 等数据库收录！ |
