Fuzzy Neuron and Its Computational Capability
-
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.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.
-
Key words:
- neural networks /
- fuzzy operators /
- orders /
- computational capability /
- Turing equivalence
-
[1] 李晓忠, 汪培庄, 罗承忠. 模糊神经网络[M]. 贵阳:贵州科技出版社, 1994. [2] 刘晓鸿, 戴汝为. 线性阈值单元神经元网络的图灵等价性[J]. 计算机学报, 1995,18(6):438~442. [3] Cutland N. Computability: An introduction to recursive function theory . Cambridge: Cambridge Univ Press, 1980. [4] 孟祥武, 程 虎. Hopfield网的图灵等价性[J]. 软件学报, 1998,9(1):43~46. -
点击查看大图
计量
- 文章访问数: 2404
- HTML全文浏览量: 50
- PDF下载量: 692
- 被引次数: 0
下载:
