Title | ||
---|---|---|
Breaking Rotational Symmetry in a Self-Organizing Map Model for Orientation Map Development |
Abstract | ||
---|---|---|
We analyze the pattern formation behavior of a high-dimensional self-organizing map (SOM) model for the competitive projection of ON-center-type and OFF-center-type inputs to a common map layer. We mathematically show, and numerically confirm, that even isotropic stimuli can drive the development of oriented receptive fields and an orientation map in this model. This result provides an important missing link in the spectrum of pattern formation behaviors observed in SOM models. Extending the model by including further layers for binocular inputs, we also investigate the combined development of orientation and ocular dominance maps. A parameter region for combined patterns exists; corresponding maps show a preference for perpendicular intersection angles between iso-orientation lines and ocularity domain boundaries, consistent with experimental observations. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1162/089976698300017719 | Neural Computation |
Keywords | Field | DocType |
spectrum,pattern formation,receptive field,ocular dominance | Receptive field,Isotropy,Perpendicular,Image processing,Self-organizing map,Artificial intelligence,Artificial neural network,Geometry,Computer vision,Rotational symmetry,Mathematical optimization,Pattern formation,Mathematics | Journal |
Volume | Issue | ISSN |
10 | 3 | 0899-7667 |
Citations | PageRank | References |
4 | 0.90 | 6 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Maximilian Riesenhuber | 1 | 761 | 59.73 |
Hans-ulrich Bauer | 2 | 236 | 38.94 |
D. Brockmann | 3 | 4 | 1.24 |
Theo Geisel | 4 | 314 | 40.09 |