Self-organizing maps with refractory period

被引:0
作者
Neme, Antonio [1 ]
Mireles, Victor [2 ]
机构
[1] Univ Autonoma Ciudad Mexico, Mexico City, DF, Mexico
[2] Univ Nacl Autonoma Mexico, Mexico City, DF, Mexico
来源
ARTIFICIAL NEURAL NETWORKS - ICANN 2007, PT 2, PROCEEDINGS | 2007年 / 4669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
Self-organizing map (SOM) has been studied as a model of map formation in the brain cortex. Neurons in the cortex present a refractory period in which they are not able to be activated, restriction that should be included in the SOM if a better description is to be achieved. Altough several works have been presented in order to include this biological restriction to the SOM, they do not reflect biological plausibility. Here, we present a modification in the SOM that allows neurons to enter a refractory period (SOM-RP) if they are the best matching unit (BMU) or if they belong to its neighborhood. This refractory period is the same for all affected neurons, which contrasts with previous models. By including this biological restriction, SOM dynamics resembles in more detail behavior shown by the cortex, such as non-radial activity patterns and long distance influence, besides the refractory period. As a side effect, two error measures are lower in maps formed by SOM-RP than in those formed by SOM.
引用
收藏
页码:369 / +
页数:3
相关论文
共 21 条
[1]  
[Anonymous], 2000, SELF ORG MAPS
[2]  
[Anonymous], [No title captured]
[3]   Neural maps and topographic vector quantization [J].
Bauer, HU ;
Herrmann, M ;
Villmann, T .
NEURAL NETWORKS, 1999, 12 (4-5) :659-676
[4]  
BEDNAR J, 2004, SCALING SELF ORG MAP
[5]   THE TEMPORAL KOHONEN MAP [J].
CHAPPELL, GJ ;
TAYLOR, JG .
NEURAL NETWORKS, 1993, 6 (03) :441-445
[6]   Winner-relaxing self-organizing maps [J].
Claussen, JC .
NEURAL COMPUTATION, 2005, 17 (05) :996-1009
[7]   Theoretical aspects of the SOM algorithm [J].
Cottrell, M ;
Fort, JC ;
Pagès, G .
NEUROCOMPUTING, 1998, 21 (1-3) :119-138
[8]   SELF-ORGANIZING MAPS - ORDERING, CONVERGENCE PROPERTIES AND ENERGY FUNCTIONS [J].
ERWIN, E ;
OBERMAYER, K ;
SCHULTEN, K .
BIOLOGICAL CYBERNETICS, 1992, 67 (01) :47-55
[9]  
GOODHILL G, 1996, 3 JOINT S NEUR COMP, P61
[10]   Analysis of the elastic net model applied to the formation of ocular dominance and orientation columns [J].
Goodhill, GJ ;
Cimponeriu, A .
NETWORK-COMPUTATION IN NEURAL SYSTEMS, 2000, 11 (02) :153-168