The influence of a clipping procedure on the properties of vector associative memory is investi-gated. The analysis is performed for the particular case of a phase model of a parametric neural network with2q-state neurons. The critical network size N, is found. It is shown that, for small network sizes (N < N,,), theclipping leads to an increase of the storage capacity and enhances the network ability to retrieve strongly dis-torted patterns. Clipping of bigger networks (N > N(.) leads to a deterioration of the recognition ability andreduces the storage capacity.
展开▼
