Self-Organization with Lateral Connections

A self-organizing neural network model for the development of aaerent and lateral input connections in cortical feature maps is presented. The weight adaptation process is purely activity-dependent, unsupervised, and local. The aaerent input weights self-organize into a topological map of the input space. At the same time, the lateral interaction weights develop a smooth \Mexican hat" shaped distribution. Weak lateral connections die oo, leaving a pattern of connections that represents the signiicant long-term correlations of activity on the feature map. The model demonstrates how self-organization can bootstrap itself based on input information only, without global supervision or predetermined lateral interaction. The model can potentially account for experimental observations such as critical periods for self-organization in cortical maps and development of horizontal connections in the primary visual cortex.