A Neural Network with Low Symmetric Connectivity
Timothy L. H. Watkin, David C. Sherrington · Europhysics Letters (EPL) · 1991
We present the complete, equilibrium solution of a neural-network model in which each neuron is connected to a small fraction of the others by symmetric, Hebb-rule synapses. At first replica symmetry is assumed, but the results are then corrected for full symmetry breaking, which leads to a substantial increase in storage capacity.