Results from the Gardner-Derrida-Mottishaw theory of associative memory

Neural Netw. 1999 Mar;12(2):247-257. doi: 10.1016/s0893-6080(98)00129-4.

Abstract

General computable formulas for overlap and the other parameters are derived from the Gardner-Derrida-Mottishaw theory of associative memory on the Little-Hopfield model. The overlap is expressed in terms of integral of many-dimensional Gaussian functions. A method of approximation is developed to make numerical computation easy. It is shown that the numerical results are totally in good agreement with simulation.