A model for self-organization in WTA networks and its application to map prediction problems

A mathematical model for long-term memory (LTM) reorganization in self-organizing winner-take-all (WTA) networks is developed. The model describes the temporal evolution of the density of neural LTM states using a diffusive partial differential equation. Solutions to this equation show that, in the long run, LTM states tend to cluster about the modes of the stimulating source's probability density function. This behavior is precisely what is required by many engineering problems involving maximum a posteriori (MAP) prediction. The connection between self-organizing WTA networks and MAP prediction is discussed. A simulated example demonstrating this connection is provided.<
>