Critical storage capacity of the J = ± 1 neural network
Werner Krauth, Manfred Opper · Journal of Physics A Mathematical and General · 1989
For neural networks in which the coupling J ij are allowed to take on the values J ij = 1 or J ij = -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 α c ≈ 0.82 (N → ∞ ).