Rotation-invariant pattern recognition: A procedure slightly inspired on olfactory system and based on Kohonen network

被引：0
|
作者：
Palermo, M. B.
Monteiro, L. H. A.
机构：
[1] Univ Presbiteriana Mackenzie, Posgrad Engn Elect, Escola Engn, BR-01302907 Sao Paulo, Brazil
[2] Univ Sao Paulo, Dept Engn Telecommun & Controle, Escola Politecn, BR-05508900 Sao Paulo, Brazil
来源：
ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 2 | 2006年 / 4132卷
关键词：
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：
A computational scheme for rotation-invariant pattern recognition based on Kohonen neural network is developed. This scheme is slightly inspired on the vertebrate olfactory system, and its goal is to recognize spatiotemporal patterns produced in a two-dimensional cellular automaton that would represent the olfactory bulb activity when submitted to odor stimuli. The recognition occurs through a multi-layer Kohonen network that would represent the olfactory cortex. The recognition is invariant to rotations of the patterns, even when a noise lower than 1% is added.
引用
收藏
页码：444 / 450
页数：7
相关论文
共 50 条
12345