论文信息 - High storage capacity in the Hopfield model with auto-interactions—stability analysis

High storage capacity in the Hopfield model with auto-interactions—stability analysis

Recent studies point to the potential storage of a large number of patterns in the celebrated Hopfield associative memory model, well beyond the limits obtained previously. We investigate the properties of new fixed points to discover that they exhibit instabilities for small perturbations and are therefore of limited value as associative memories. Moreover, a large deviations approach also shows that errors introduced to the original patterns induce additional errors and increased corruption with respect to the stored patterns.

[1] J. J. Hopfield,et al. ‘Unlearning’ has a stabilizing effect in collective memories , 1983, Nature.

[2] Sompolinsky,et al. Storing infinite numbers of patterns in a spin-glass model of neural networks. , 1985, Physical review letters.

[3] D. Saad,et al. The TAP Approach to Intensive and Extensive Connectivity Systems , 2001 .

[4] Extended memory loading capacity of a neutral network model with delayed time interaction , 1992 .

[5] Giancarlo Ruocco,et al. On the Maximum Storage Capacity of the Hopfield Model , 2017, Frontiers Comput. Neurosci..

[6] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[7] John J. Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities , 1999 .

[8] M. Mézard. Mean-field message-passing equations in the Hopfield model and its generalizations. , 2016, Physical review. E.

[9] J. Knott. The organization of behavior: A neuropsychological theory , 1951 .

[10] Sompolinsky,et al. Spin-glass models of neural networks. , 1985, Physical review. A, General physics.