| 模糊神经元及其计算能力研究 |
| |
| 引用本文： | 梁久祯,何新贵.模糊神经元及其计算能力研究[J].北京航空航天大学学报,2001,27(5):589-592. |
| |
| 作者姓名： | 梁久祯 何新贵 |
| |
| 作者单位： | 1.北京航空航天大学 计算机科学与工程系 |
| |
| 摘 要： | 分析了模糊神经元模型,指出了这种神经元模型在计算能力上的缺陷.提出了对模糊神经元定义的两种改进方法,一是限制传递函数为非单调函数;二是修改定义域.对改进后的模糊神经元网络证明了计算能力与图灵机的等价性,从而对传统的神经网络作了进一步推广.还对混合模糊神经网络的特点做了简单的讨论.
|
| 关 键 词： | 神经网络 模糊算子 序 计算能力 图灵等价性 |
| 文章编号： | 1001-5965(2001)05-0589-04 |
| 收稿时间： | 2000-03-07 |
| 修稿时间： | 2000年3月7日 |
Fuzzy Neuron and Its Computational Capability |
| |
| LIANG Jiu-zhen,HE Xin-gui.Fuzzy Neuron and Its Computational Capability[J].Journal of Beijing University of Aeronautics and Astronautics,2001,27(5):589-592. |
| |
| Authors: | LIANG Jiu-zhen HE Xin-gui |
| |
| Institution: | 1.Beijing University of Aeronautics and Astronautics, Dept. of Computer Science and Engineering2. Beijing Institute of System Engineering |
| |
| Abstract: | Based on analysis of the limitations of computational capability of a fuzzy neuron model, two improved methods on the definition of fuzzy neuron model are presented, by using non monotonous function as restricted inspiring function and by modifying the definition domain. For the improved fuzzy neuron models, computational capability equivalence to Turing Machine is proved. The proposed models are proved to be generalizations of traditional neural networks. Finally, the characteristics of mix fuzzy neural networks are discussed. |
| |
| Keywords: | neural networks fuzzy operators orders computational capability Turing equivalence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《北京航空航天大学学报》浏览原始摘要信息 |
| 点击此处可从《北京航空航天大学学报》下载免费的PDF全文 |
