DYNAMICS OF FULLY CONNECTED NEURAL NETWORKS WITH SIGN CONSTRAINTS
M. GUSSO, Carmela Marangi, G. Nardulli, G. Pasquariello · International Journal of Modern Physics C · 1992
We consider fully connected neural networks near saturation, trained by a modified Edinburgh algorithm, with sign constraints on the synaptic couplings. We study the domains of attraction of the stored patterns for both the balanced and the unbalanced case (excess of positive over negative constraints). A comparison with the dilute network is also included.