The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
yi zhong shi kong mo shi shi bie de zong he shen jing wang luo mo xing
Author(s): 
Pages: 271-277
Year: Issue:  3
Journal: Pattern Recognition and Artificial Intelligence

Keyword:  神经网络模式识别时序时空模式;
Abstract: 本文提出一种用于时空模式识别的综合神经网络模型,称为TS-LM-SOFM.该模型高层是一种单层时序整合网络,称为TS(Temporal Sequence)网络.TS网络以稀疏激励模式作为输入,由于神经元的兴奋性衰减作用,存储记忆的时序模式会在空间上逐渐展开,变换为抽象的空间模式.该模型底层是SOFM(Self-Organizing Feature Map),其作用是空间模式整合与实际信号的特征检测.LM(Learning Matrix)作为TS与LM的中间过渡层.利用TS-LM-SOFM对超声导航的机器人实际采集的数据进行处理,实验表明,TS-LM-SOFM神经网络输出的模式能够较好地抽象表示输入信号的时空特征.
Related Articles
No related articles found