An analysis of the local stability of the error-free memory pattern solutions for a new type of oscillatory model of associative memory was discussed. The model includes an extra, second-order Fourier mode in the coupling function, which enables us to control the stability of the solutions for all patterns and to distinguish the memory pattern form others by their stabilities. This model was closely related to the cumulative distribution function of spikes in neural networks. The capacity of model turns out to follow the same scaling with the number of neurons as in the case of the classical Hopfield model, but with a prefactor that depends on the relative strength of the second-order mode.
ASJC Scopus subject areas
- Physics and Astronomy(all)