A vector model of associative memory with clipped synapses

The influence of a clipping procedure on the properties of vector associative memory is investigated. The analysis is performed for the particular case of a phase model of a parametric neural network with 2q-state neurons. The critical network size N c is found. It is shown that, for small network sizes (N < N c ), the clipping leads to an increase of the storage capacity and enhances the network ability to retrieve strongly distorted patterns. Clipping of bigger networks (N > N c ) leads to a deterioration of the recognition ability and reduces the storage capacity.