Object Recognition using a Bayesian Network imitating Human Neocortex

被引:0
作者
Wang, Lei [1 ,2 ]
Wen, Xianbin [1 ,2 ]
Jiao, Xu [1 ,2 ]
Zhang, Jianguang [1 ,2 ]
机构
[1] Tianjin Univ Technol, Minist Educ, Key Lab Comp Vis & Syst, Tianjin 300191, Peoples R China
[2] Tianjin Key Laboratory of Intelligence Comp, Novel Software Technol, Tianjin 300191, Peoples R China
来源
PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9 | 2009年
基金
中国国家自然科学基金;
关键词
Object recognition; Bayesian network; Hierarchical Temporal Memory; mammalian neocortex;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
After Mountcastle proposed the theory that all parts of mammalian neocortex are uniform Ill, more and more evidences were found to prove that no matter what function the field of neocortex provide, the organizing of cortex cells are same and have an hierarchical structure. It can be inferred every unit of neocortex process information using an identical algorithm. This means if people can find and imitate this algorithm, all intelligence work will be resolved in one way, the only difference is using different sensors. Base on this, Hawkins proposed a top-down model of neocortical operation 121, in which model, both continuous time and prediction play important roles in human's invariant recognition. Then George and Hawkins developed an inspired framework named "Hierarchical Temporal Memory" 131, using a hierarchical Bayesian network to perform prediction and temporal sequence in training the network, which partially implements Hawkins' model, and can provide a rather good performance in invariant recognition. We current study is extending their work by implementing the framework in visual category recognition field.
引用
收藏
页码:2645 / 2649
页数:5
相关论文
共 23 条