Double synaptic weight neuron theory and its application | |
Wang SJ ; Chen X ; Qin H ; Li WJ ; Bian Y | |
刊名 | advances in natural computation |
2005 | |
卷号 | pt 1 proceedings 3610期号:0页码:264-272 |
ISSN号 | 0302-9743 |
通讯作者 | wang, sj, chinese acad sci, inst semicond, lab artificial neural networks, beijing 100083, peoples r china. 电子邮箱地址: wsjue@red.semi.ac.cn ; shendacx@163.com ; qinhong@red.semi.ac.cn ; wjli@red.semi.ac.cn ; bianyi@yeah.net |
中文摘要 | in this paper, a novel mathematical model of neuron-double synaptic weight neuron (dswn)(l) is presented. the dswn can simulate many kinds of neuron architectures, including radial-basis-function (rbf), hyper sausage and hyper ellipsoid models, etc. moreover, this new model has been implemented in the new cassann-ii neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. the flexibility of the dswn has also been described in constructing neural networks. based on the theory of biomimetic pattern recognition (bpr) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on cassann-ii neurocomputer. in these two special cases, the result showed dswn neural network had great potential in pattern recognition. |
学科主题 | 人工智能 |
收录类别 | SCI |
语种 | 英语 |
公开日期 | 2010-03-17 |
内容类型 | 期刊论文 |
源URL | [http://ir.semi.ac.cn/handle/172111/8464] |
专题 | 半导体研究所_中国科学院半导体研究所(2009年前) |
推荐引用方式 GB/T 7714 | Wang SJ,Chen X,Qin H,et al. Double synaptic weight neuron theory and its application[J]. advances in natural computation,2005,pt 1 proceedings 3610(0):264-272. |
APA | Wang SJ,Chen X,Qin H,Li WJ,&Bian Y.(2005).Double synaptic weight neuron theory and its application.advances in natural computation,pt 1 proceedings 3610(0),264-272. |
MLA | Wang SJ,et al."Double synaptic weight neuron theory and its application".advances in natural computation pt 1 proceedings 3610.0(2005):264-272. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论