论文信息 - Simulating highly diluted neural networks

Simulating highly diluted neural networks

The asymmetric diluted Hopfield model is studied through numerical simulations and reliable results are obtained even when the network sizes are not exponentially large. The mean final overlap, the mean convergence time and a quantity that gives information on the relative importance of spurious states are measured as a function of the load capacity alpha .

Jeferson Jacob Arenzon | J. J. Arenzon | Ney Lemke | N. Lemke

[1] B. Forrest. Content-addressability and learning in neural networks , 1988 .

[2] Finite temperature study of retrieval time in Hopfield network , 1992 .

[3] G. Kohring,et al. Slowing down of retrieval in the hopfield model , 1990 .

[4] Kanter. Convergence time in infinite-range neural networks with parallel dynamics at zero temperature. , 1989, Physical review. A, General physics.

[5] Arenzon,et al. Neural networks with high-order connections. , 1993, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[6] G. Kohring,et al. COMMENT: Convergence time and finite size effects in neural networks , 1990 .

[7] H. Bernas,et al. Depairing-like variation of Tc in YBa2Cu3O7−δ , 1990 .

[8] E. Gardner,et al. An Exactly Solvable Asymmetric Neural Network Model , 1987 .