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

奇偶校验问题的二进神经网络学习算法

Learning Algorithm of Binary Neural Networks for Parity Problems
下载PDF
导出
摘要 二进神经网络可以完备表达任意布尔函数,但对于孤立节点较多的奇偶校验问题却难以用简洁的网络结构实现。针对该问题,提出了一种实现奇偶校验等孤立节点较多的一类布尔函数的二进神经网络学习算法。该算法首先借助蚁群算法优化选择真节点及伪节点的访问顺序;其次结合几何学习算法,根据优化的节点访问顺序给出扩张分类超平面的步骤,从而减少隐层神经元的数目,同时给出了隐层神经元及输出元的表达形式;最后通过典型实例验证了该算法的有效性。 Binary neural network can completely express arbitrary Boolean function,but more isolated nodes such as parity problem are difficult to implement with simple network structure.According to this problem,we presented a learning algorithm to realize Boolean function such as parity problems with many isolated samples.By means of the ant colony algorithm,we obtained the optimized core nodes and the extension order of true and false nodes,by combing the geometrical algorithm,we gave the steps of how to expand the classifier hyperplanes with the optimized core nodes,so this algorithm can reduce the number of hidden neurons in network,and the expression of the hidden neurons and the output neuron are also given.Finally,this algorithm is validated to be effective through examples.
作者 杨娟 陆阳 朱晓娟 邱述威
机构地区 合肥工业大学计算机与信息学院 安徽省矿山物联网与安全监控技术重点实验室
出处 《计算机科学》 CSCD 北大核心 2013年第1期236-240,共5页 Computer Science
基金 国家自然科学基金项目(61070220) 国家"863"计划项目(2011AA060406) 高等学校博士学科点专项科研基金(20090111110002)资助
关键词 二进神经网络 布尔函数 奇偶校验问题 蚁群算法 Binary neural networks Boolean function Parity problems Ant colony algorithm
分类号 TP18 [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11

  • 1Chen Fang-yue,Chen Guan-rong,He Guo-long. Universal Perceptron and DNA-Like Learning Algorithm for Binary Neural Networks:LSBF and PBF Implementations[J].IEEE Transactions on Neural Networks,2009,(10):1645-1658.
  • 2Chen Fang-yue,Chen Guan-rong,He Qin-bin. Universal Perceptron and DNA-Like Learning Algorithm for Binary Neural Networks:Non-LSBF Implementation[J].IEEE Transactions on Neural Networks,2009,(08):1293-1301.
  • 3Lu Yang,Yang Juan,Wang Qiang. The upper bound of the minimal number of hidden nodes in parity problem by neural networks[J].Science in China(Information Sciences),2007,(07).
  • 4Chaudhari N S;Tiwari A.Binary Neural Network classifier and it's bound for the number of hidden layer neurons[A]新加坡,2010.
  • 5Shimada M,Satio T. A GA-based learning algorithm for binary neural networks[J].IEICE Transactions on Fundamentals,2002,(11):2544-2546.
  • 6Hirane T,Toryu T,Nakano H. Analysis for Characteristics of GA-Based Learning Method of Binary Neural Networks[A].2005.323-329.
  • 7杨娟,陆阳,方欢,朱晓娟.基于蚁群算法的二进神经网络学习算法[J].电路与系统学报,2012,17(6):49-55. 被引量：3
  • 8Kim J H,Park S K. The geometrical learning of binary neural networks[J].IEEE Transactions on Neural Networks,1995,(01):237-247.
  • 9Fung H K,Li L K. Minimal feedforward parity networks using threshold gates[J].Neural Computation,2001,(02):319-326.
  • 10高尚;杨静宇.群智能算法及其应用[M]北京:中国水利水电出版社,2006.

二级参考文献21

  • 1Chen Fangyue, Chen Guanrong, He Guolong. Universal Perceptron and DNA-Like Learning Algorithm for Binary Neural Networks: LSBF and PBF Implementations [J]. IEEE Transactions on Neural Network, 2009, 20(10): 1645-1658.
  • 2Chen Fangyue, Chen Guanrong, He Qinbin. Universal Perceptron and DNA-Like Learning Algorithm for Binary Neural Networks: Non-LSBF Implementation [J]. IEEE Transactions on Neural Network, 2009, 20(8): 1293-1301.
  • 3Changbing Tang, Fangyue Chert, Xiang Li. Perceptron implementation of Triple-Valued logic operations [J]. IEEE Transaction on Circuits and Systems-ll: Express Brieh 2011, 58(9): 590-594.
  • 4Lu Yang, Yang Juan, Wang Qiang, Huang Zhenjin. The upper bound of the minimal number of hidden nodes in parity problem by neural networks [J]. Science in China Ser.F Information Sciences, to be published.
  • 5Naredra S. Chaudhari, Aruna Tiwari. Binary Neural Network classifier and it's bound for the number of hidden layer neurons [A] International conference on Control Automation Robotics and Vision [C]. Singapore, 2010-12.
  • 6D L Gray, A N Michel. A training algorithm for binary feedforward neural networks [J]. IEEE Trans. Neural Networks, 1993, 3(2): 176-194.
  • 7Kim J H, Park S K. The geometrical learning of binary neural networks [J]. IEEE Trans Neural Networks, 1995, 6(1): 237-247.
  • 8A Yamamoto, T Saito. An improved expand-and-truncate learning [A]. IEEE International Conference on Neural Networks Proceedings [C]. Houston, TX, USA, 1997-06： 1 11 - 1 116.
  • 9Ma Xiaomin, ：ang Yixian, Zhang Zhaozhi. Constructive learning of binary neural networks and its application to nonlinear register synthesis [A]. International conference on neural information Proceedings [C]. Shanghai, China, 2001-11, 1: 90-95.
  • 10Di Wang, N S Chaudhari. A multi-core learning algorithm for binary neural networks [A]. International Joint Conference an Neural Networks Proceedings [C]. Portland, Oregon, USA, 2003-07, 1: 450-455.

共引文献6

计算机科学
2013年 第1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