Abstract
The author describes the dynamics of a neuron layer with reciprocal inhibition. In the presence of noise the layer works as a selector, performing random choice of a single neuron from the set of neurons with the maximum level of excitation. He discusses the following topics: two-basic-layer architectures with reciprocal inhibition; the Laplace transforms of the transients in the intervals between switching: transient response to a step input; regime of dominating: winner take all; hysteresis; periodic inhibition and the 'elementary operation' of random choice; and the regime of contrasting. A simple example of an associative neural network is presented. The paper is aimed at understanding the general architecture of the associative learning systems of the brain.

This publication has 2 references indexed in Scilit: