An improved ART2 neural network: Resisting pattern drifting through generalized similarity and confidence measures
An improved ART2 neural network: Resisting pattern drifting through generalized similarity and confidence measures
复制标题
改进的 ART2 神经网络：通过广义相似性和置信度测量来抵抗模式漂移
DOI：
10.1016/j.neucom.2014.12.055
复制
发表时间：
2015-05
期刊：
影响因子：
6
通讯作者：
Yuezhong Song
中科院分区：
文献类型：
--
作者：
Haifeng Li;Chang Gao;Lin Ma;Yuezhong Song
ART2网络是一种基于自适应共振理论的无监督神经网络，具有响应速度快、学习实时等优点，在实时分类中得到了广泛的应用。传统的ART 2网络存在两个问题：相位相似的样本难以区分和渐变数据引起的模式漂移。本文提出了一种基于广义相似性和置信度测度的改进ART2网络，称为GSC-ART2（广义相似性置信ART2）网络。在该神经网络中，提出了基于广义相似性测度的相似性检测机制，解决了相位相似的不同样本难以区分的问题。此外，提出了综合考虑广义相似度和置信度的连接权值更新方法，以抑制模式漂移问题。仿真实验结果表明，GSC-ART2网络在分类和抑制模式漂移方面优于传统ART2网络。GSC-ART2网络将成为各种应用中模式漂移问题的通用解决方案。
ART2 network is a kind of non-supervised neural network based on the adaptive resonance theory, and has been widely used in real-time classification because of its rapid response and real-time learning. There are two problems in the traditional ART2 network: the indistinguishable of the different samples with similar phase and the pattern drifting caused by the gradual changing data. In this paper, we propose an improvement version of the ART2 network based on the generalized similarity and confidence measures, named GSC-ART2 (Generalized Similarity Confidence ART2) network. In this neural network, the similarity detection mechanism based on the generalized similarity measure is proposed to solve the indistinguishable problem of the different samples with similar phase. Furthermore, the updating method of the connection weights considering both the generalized similarity and the confidence measures is proposed to inhibit pattern drifting problem. The stimulation data is created to evaluate the proposed GSC-ART2 network, and the outcomes approved that the performance of the GSC-ART2 network is better than traditional ART2 network about the classification and the inhibiting pattern drifting. The GSC-ART2 network would become a universal solution to the pattern drifting problem in various applications.
登录
查看更多内容
DOI：
10.1109/cecnet.2012.6202189
发表时间：
2012-04
期刊：
2012 2nd International Conference on Consumer Electronics, Communications and Networks (CECNet)
影响因子：
--
作者：
Yuehui Peng;Shuguang Liu;Yanyan Zhang
通讯作者：
Yuehui Peng;Shuguang Liu;Yanyan Zhang
DOI：
10.1016/j.proeng.2012.01.594
发表时间：
2012
期刊：
Procedia Engineering
影响因子：
--
作者：
Maryam Hourali;G. Montazer
通讯作者：
Maryam Hourali;G. Montazer
DOI：
10.1109/tcsi.2010.2092151
发表时间：
2011-05
期刊：
IEEE Transactions on Circuits and Systems I: Regular Papers
影响因子：
--
作者：
Lixian Zhang;Naigang Cui;Ming Liu;Ye Zhao
通讯作者：
Lixian Zhang;Naigang Cui;Ming Liu;Ye Zhao
DOI：
10.4249/scholarpedia.1569
发表时间：
1997-07
期刊：
--
影响因子：
--
作者：
S. Grossberg
通讯作者：
S. Grossberg
DOI：
10.1007/978-3-642-37149-3_6
发表时间：
2013-04
期刊：
--
影响因子：
--
作者：
Mingming Wang;Mingming Wang;Xiaozhu Lin
通讯作者：
Mingming Wang;Mingming Wang;Xiaozhu Lin