Power law decay of stored pattern stability in sparse Hopfield neural networks

Fei Fang,Zhou Yang,Sheng-Jun Wang

Figure 1. The overlap difference φ − φ0 versus the number of patterns n on scale-free networks on a log-log scale. The blue dashed line is the analytic results. Squares represent the simulation results. The red solid line is the fitted line. Data points from n=2 to 2500 are used in fitting. The parameters are N=10 000, average degree ⟨k⟩=4. Inset: the overlap φ versus the number of patterns n on scale-free networks on a log-log scale. The final overlap φ0 is 0.24. Each data point is the average over 1000 realizations.