How Lateral Interaction Develops In A Self-Organizing Feature Map (1993)
A biologically motivated mechanism for self-organizing a neural network with modifiable lateral connections is presented. The weight modification rules are purely activity-dependent, unsupervised and local. The lateral interaction weights are initially random but develop into a Mexican hat'' shape around each neuron. At the same time, the external input weights self-organize to form a topological map of the input space. The algorithm demonstrates how self-organization can bootstrap itself using input information. Predictions of the algorithm agree very well with experimental observations on the development of lateral connections in cortical feature maps.
View:
PDF, PS
Citation:
In Proceedings of the IEEE International Conference on Neural Networks (San Francisco, CA), 1360-1365, 1993. Piscataway, NJ: IEEE.
Bibtex:

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