二进神经网络的模式匹配学习
The pattern match learning of binary neural networks
-
摘要: 二进神经网络的知识提取需要了解每个神经元的逻辑意义。一般来说,对二进神经网络学习结果的分析是困难的。该文提出了一种基于线性可分结构系结构分析的学习算法,采用这种方法对布尔空间的样本集合进行学习,得到的二进神经网络隐层神经元都归属于一类或几类线性可分结构系,只要这几类线性可分结构系的逻辑意义是清晰的,就可以分析整个学习结果的知识内涵。
-
关键词:
- 二进神经网络; 线性可分; 模式匹配
Abstract: It is necessary to know the logical meaning of every binary neuron when extracting knowledge from a binary neural network. Generally, it is difficult, to analyze learning results of a learning algorithm for binary neural networks. Ln this paper, a new learning method is presented which is based on analyzing a set of linear separable structures. The most important benefit of this method is all binary neurons belong to one or more types of linear separable structure sets. If those linear separable structure sets have clear logical meaning, the whole knowledge of binary neural networks can be dug out. -
陆阳,韩江洪,高隽,魏臻,二进神经网络中汉明球的逻辑意义及一般判别方法,计算机研究与发展,2002,39(1),79-86 ［2］J.H.Kim,S.Park,The geometrical learning of binary neural networks,IEEE Trans.on Neural Networks,1995,6(1),237-247. ［3］朱大铭,马绍汉,二进制神经网络分类问题的几何学习算法,软件学报,1997,8(8),622-629. ［4］马晓敏,杨义先,章照止,一种新的阈函数的分析框架及有关结论,计算机学报,2000,23(3),225-230. ［5］陆阳,韩江洪,张维勇,二进神经网络逻辑关系判据及等价性规则提取,模式识别与人工智能,2001,14(2),171-176. ［6］陆阳,韩江洪,高隽,二进神经网络隐元数目最小上界研究,模式识别与人工智能,2000,13(3),254-257. ［7］马晓敏,杨义先,章照止,二进神经网络学习算法研究,计算机学报,1999,22(9),931-935. -
计量
- 文章访问数: 2373
- HTML全文浏览量: 93
- PDF下载量: 518
- 被引次数: 0
下载:
