Power law decay of stored pattern stability in sparse Hopfield neural networks
|
Power law decay of stored pattern stability in sparse Hopfield neural networks |
| Fei Fang,Zhou Yang,Sheng-Jun Wang |
| Figure 11. The overlap difference φ − φ0 versus the number of patterns n on ER random networks on a log-log scale. Parameters are the average degree ⟨k⟩=50. The size of networks respectively is N=10 000(squares), 20 000(circles), 40 000(upper triangles), 80 000(lower triangles) and 16 000(diamonds). Inset: the overlap φ versus the number of patterns n on random networks on a linear coordination. Each data point is averaged over 1000 realizations. |
|
|