Self-Organizing Feature Maps With Lateral Connections: Modeling Ocular Dominance (1994)
A self-organizing neural network model called LISSOM for the synergetic development of afferent and lateral connections in cortical feature maps is presented. The model demonstrates that both ocular dominance columns and the lateral connectivity between them could result by a dimension reduction mapping from a 3D space of two retinotopic coordinates and an ocular dominance parameter to a 2D neural sheet.
In M. C. Mozer and P. Smolensky and D. S. Touretzky and J. L. Elman and A. S. Weigend, editors, Proceedings of the 1993 Connectionist Models Summer School, 31-38, 1994.

Risto Miikkulainen Faculty risto [at] cs utexas edu
Joseph Sirosh Ph.D. Alumni joseph sirosh [at] gmail com

The LISSOM package contains the C++, Python, and Scheme source code and examples for training and testing firing-rate...