Self-Organizing Maps With Homogeneous Refractory Periods

Self-organizing map (SOM) has been studied as a model of map formation in the brain cortex. However, the original model present several oversimplifications. For example, 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 model is to be achieved. Although several modifications have been studied 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 the 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

[1]  Pedro Miramontes,et al.  A Parameter in the Learning Rule of SOM That Incorporates Activation Frequency , 2006, ICANN.

[2]  Richard F. Thompson,et al.  The Brain: A Neuroscience Primer , 1993 .

[3]  Teuvo Kohonen,et al.  Self-organizing neural projections , 2006, Neural Networks.

[4]  G. Goodhill,et al.  Analysis of the elastic net model applied to the formation of ocular dominance and orientation columns. , 2000, Network.

[5]  Klaus Schulten,et al.  Self-organizing maps: ordering, convergence properties and energy functions , 1992, Biological Cybernetics.

[6]  Michel Verleysen,et al.  2002 Special Issue Self-organizing maps with recursive neighborhood adaptation , 2002 .

[7]  Thomas Villmann,et al.  Neural maps and topographic vector quantization , 1999, Neural Networks.

[8]  José Carlos Príncipe,et al.  Principles and networks for self-organization in space-time , 2002, Neural Networks.

[9]  John G. Taylor,et al.  The temporal Kohönen map , 1993, Neural Networks.

[10]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

[11]  Dmitri B. Chklovskii,et al.  Orientation Preference Patterns in Mammalian Visual Cortex A Wire Length Minimization Approach , 2001, Neuron.

[12]  Risto Miikkulainen,et al.  Scaling self-organizing maps to model large cortical networks , 2001, Neuroinformatics.

[13]  Mimi Liljeholm,et al.  Quantitative analysis of kernel properties in Kohonen's self-organizing map algorithm: Gaussian and difference of Gaussians neighborhoods , 2002, Neurocomputing.

[14]  T. Sejnowski,et al.  Quantifying neighbourhood preservation in topographic mappings , 1996 .

[15]  Gilles Pagès,et al.  Theoretical aspects of the SOM algorithm , 1998, Neurocomputing.

[16]  T. Villmann,et al.  Topology Preservation in Self-Organizing Maps , 1999 .

[17]  J. Michael Herrmann,et al.  Retinotopy and spatial phase in topographic maps , 2000, Neurocomputing.