期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

二进神经网络中笛卡尔球的研究 被引量：3

STUDY OF CARTESIAN SPHERE IN BINARY NEURAL NETWORKS
原文传递
导出
摘要 根据两类线性可分结构笛卡尔积的概念,定义了布尔空间中笛卡尔球的概念,证明了笛卡尔球是一类线性可分结构系.此外,还对以布尔空间中任意样本Ⅹ°为中心,与Ⅹ°之间Hamming距离为1的任意个样本与Ⅹ°组成的集合进行了研究,证明了这是一类笛卡尔球.为了对笛卡尔球进行规则提取,文中还分析了笛卡尔球的逻辑意义,建立了二进神经网络中判别笛卡尔球的一般方法,描述了这种判别方法的具体步骤,并通过一个实例说明了在二进神经网络中判别笛卡尔球的过程. This paper gives the definition of Cartesian sphere according to Cartesian product of two Linear Separability(LS)structure series, and it proves that Cartesian sphere is a LS structure series. Furthermore, a kind of set, which is grouped by X'and any samples whose hamming distance with X^(?)are 1, is studied. It is proved to be Cartesian sphere. In order to extract rules from Cartesian sphere, the logical meaning of Cartesian sphere is analyzed, and a general judging method of Cartesian sphere is proposed. The judging steps are given in detail, and the judging process is described through an example.
作者 陆阳 韩江洪 张维勇
机构地区 合肥工业大学计算机与信息学院
出处 《模式识别与人工智能》 EI CSCD 北大核心 2004年第3期368-373,共6页 Pattern Recognition and Artificial Intelligence
基金 安徽省重点科研计划资助项目(No.01041175)
关键词 二进神经网络 线性可分 汉明球 规则提取 Binary Neural Networks Linear Separability Hamming Sphere Rule Extraction
分类号 TP183 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献14

  • 1Chu C H, Kim J H, Kim I. Applications of Binary Neural Networks Learning to Pattern Classification. In: Proc of the IEEE World Congress on Computational Intelligence and 1994 IEEE International Conference on Neural Networks. Orlando, USA, 1994, Ⅱ: 907-911
  • 2Muselli M, Liberati D. Rule Extraction from Binary Neural Networks In: Proc of the 9th International Conference on Artificial Neural Networks. Edinburgh, UK, 1999, Ⅱ: 515-520
  • 3Kim J H, Ham B, Chen J K. The Learning of Multi-Output Binary Neural Networks for Handwritten Digit Recognition. In: Proc of the International Joint Conference on Neural Networks. San Francisco, USA, 1993, 605-608
  • 4Garcia J C S, Miyatake M N, Meana H P. An Extended Hamming Neural Networks for Non Binary Pattern Recognition. In: Proc of the 37th Midwest Symposium on Circuits and Systems. Lafayette, USA, 1994, Ⅰ: 607-609
  • 5Funabiki N, Nishikawa S, Tajima S. A Binary Neural Network Approach for Net Assignment Problems. In: Proc of the IEEE International Conference on Neural Networks. Washington DC, USA,1996, Ⅳ: 2188-2193
  • 6Kennedy J V, Austin J, Pack R. C-NNAP: A Dedicated Platform for Binary Neural Networks. In: Proc of the 5th International Conference on Artificial Neural Networks. Cambridge, UK, 1997, 161-166
  • 7Bermak A, Austin J. VLSI Implementation of a Binary Neural Network. In: Proc of the 7th International Conference on Micmelectronies for Neural, Fuzzy and Bio-Inspired Systems. Granada, Spain, 1999, 374-379
  • 8晏蒲柳,夏德麟,郭成城.计算机网络智能故障诊断知识库构造方法[J].模式识别与人工智能,2000,13(2):142-145. 被引量：4
  • 9马晓敏,杨义先,章照止.二进神经网络非线性移位寄存器的综合[J].电子学报,2000,28(1):70-73. 被引量：3
  • 10马晓敏,杨义先,章照止,吴伟陵.布尔神经网络的一种高效率学习算法[J].通信学报,1999,20(12):13-18. 被引量：5

二级参考文献35

  • 1程辉.逻辑神经元网络[J].模式识别与人工智能,1993,6(4):300-306. 被引量：5
  • 2肖国镇 王育民.伪随机充序列及其应用[M].北京:国际工业出版社,1985..
  • 3万哲先.代数与编码[M].北京:科学出版社,1979..
  • 4沈世镒.组织密码学[M].杭州:浙江科学技术出版社,1992..
  • 5Limin Fu. Rule generation from neural networks. IEEE Trans on Systems, Man, and Cybernatics, 1994, 24(8): 1114～1124
  • 6T B Ludermir. Extracting rules from feedforward Boolean neural networks. In: Proc of 5th Brazilian Symposium on Neural Networks. IEEE Press, 1998. 61～66
  • 7M Muselli, D Liberati. Rule extraction from binary neural networks. In: The 9th Int'l Conf on Artificial Neural Networks, vol 2. Brazil: IEE Press, 1999. 515～520
  • 8G G Towell, J W Sharlik. Extracting refined rules from knowledge-based neural networks. Machine Learning, 1993, 13(1): 71～101
  • 9Yu Xiang, M Ishikawa, Chi Huisheng. Logical rules extraction from data using neural networks. In: Proc of 1997 Chinese Congress on Neurocomputing Science. Nanjing, China, 1997. 293～296
  • 10朱一清，离散数学，1997年

共引文献15

同被引文献36

  • 1Gray D L,Michel A N. A training algorithm for binary feed for- ward neural networks[J]. IEEE Trans. Neural Networks, 1992, 3(2) : 176-194.
  • 2Kim J H, Park S K. The geometrical learning of binary neural networks[J]. IEEE Trans. Neural Networks, 1995,6 ( 1 ) : 237- 247.
  • 3Muselli M. On sequential construction of binary neural networks [J]. IEEE Trans Neural Networks, 1995,6(3) : 678-690.
  • 4Yamamoto A, Saito T. A flexible learning algorithm for binary neural networks[J]. IEICE Trans. Fundamentals, 1998, ES1-A (9) . 1925-1930.
  • 5Chen Fang-yue, Chen Guan-rong, He Guo-long. Universal Per- ceptron and DNA-Like Learning Algorithm for Binary Neural Networks: LSBF and PBF Implementations[J]. IEEE Transac-tions on Neural network,2009,20(10) : 1645-1658.
  • 6Chen Fang-yue, Chen Guan-rong, He Qin-bin. Universal Percep- tron and DNA-Like Learning Algorithm for Binary Neural Net- works Non-LSBF Implementation[J]. IEEE Transactions on Neural network,2009,20(8) : 1293-1301.
  • 7Lu Yang, Yang Juan, Wang Qiang, et al. The upper bound of the minimal number of hidden nodes in parity problem by neural networks[J]. Science China Information Sciences, Oct. 2011.
  • 8Chua L O. Visions of nonlinear science in the 21st century in CNN A Paradigm for Complexity[M]. Singapore: World Scien- tific, 1999.
  • 9Chen Fang-yue, He Guo-long, Chen Guan-rong. Realization of Boolean Functions via CNN: Mathematical Theory, LSBF and Template Design[J]. Circuits and Systems I Regular Papers, IEEE Transactions on, 2006,53(10) : 2203-2213.
  • 10Wegener I. The complexity of Boolean function[M]. New York: Wiley, 1987.

引证文献3

二级引证文献5

模式识别与人工智能
2004年 第3期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部