| 奇偶校验问题的二进神经网络学习算法 |
| |
| 引用本文： | 杨娟,陆阳,朱晓娟,邱述威.奇偶校验问题的二进神经网络学习算法[J].计算机科学,2013,40(1):236-240. |
| |
| 作者姓名： | 杨娟 陆阳 朱晓娟 邱述威 |
| |
| 作者单位： | (合肥工业大学计算机与信息学院 合肥230009);(安徽省矿山物联网与安全监控技术重点实验室 合肥230088) |
| |
| 基金项目： | 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 |
| |
| 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。
|
| 关 键 词： | 二进神经网络 布尔函数 奇偶校验问题 蚁群算法 |
Learning Algorithm of Binary Neural Networks for Parity Problems |
| |
| YANG Juan,LU Yang,ZHU Xiao-juan,QIU Shu-wei.Learning Algorithm of Binary Neural Networks for Parity Problems[J].Computer Science,2013,40(1):236-240. |
| |
| Authors: | YANG Juan LU Yang ZHU Xiao-juan QIU Shu-wei |
| |
| Affiliation: | 1(School of Computer and Information,Hefei University of Technology,Hefei 230009,China)1(The Anhui Provincial Key Laboratory of Mine IoT and Mine Safety Supervisory Control,Hefei 230088,China)2 |
| |
| Abstract: | 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 13oolcan function such as parity problems with many isolated samples. 13y 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. |
| |
| Keywords: | Binary neural networks Boolean function Parity problems Ant colony algorithm |
| 本文献已被 CNKI 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
