Critical storage capacity of the J = ± 1 neural network
暂无分享,去创建一个
For neural networks in which the coupling Jij are allowed to take on the values Jij = 1 or Jij = -1, the authors determine numerically the critical storage capacity for random unbiased patterns as a function of the stability. They use an exact enumeration scheme based on the Gray code and a continuous distribution for the patterns to control finite-size effects. Results are presented for N ≤ 25; they indicate an optimal storage capacity of αc ≈ 0.82 (N → ∞).
[1] E. Gardner. Maximum Storage Capacity in Neural Networks , 1987 .
[2] E. Gardner. The space of interactions in neural network models , 1988 .
[3] S. Kirkpatrick,et al. Solvable Model of a Spin-Glass , 1975 .
[4] S. Venkatesh. Epsilon capacity of neural networks , 1987 .
[5] W. Krauth,et al. Learning algorithms with optimal stability in neural networks , 1987 .