Modeling The Self-Organization Of Directional Selectivity In The Primary Visual Cortex (1999)
A model is proposed to demonstrate how neurons in the primary visual cortex could self-organize to represent the direction of motion. The model is based on a temporal extension of the Self-Organizing Map where neurons act as leaky integrators. The map is trained with moving Gaussian inputs, and it develops a retinotopic map with orientation columns that divide into areas of opposite direction selectivity, as found in the visual cortex.
View:
PDF, PS
Citation:
In Proceedings of the Ninth International Conference on Artificial Neural Networks, Erkki Oja and Samuel Kaski (Eds.), pp. 251-256, Amsterdam 1999. Elsevier.
Bibtex:

Igor Farkas Postdoctoral Alumni farkas [at] fmph uniba sk
Risto Miikkulainen Faculty risto [at] cs utexas edu