On the state transition graph of Hopfield net model

Relations of stable states between different Hopfield neural nets are shown, and upper bounds to their transient lengths are given. The proofs of the results lie in examining the sinks and the maximum path length of the state transition graph. If W is the weight matrix of a Hopfield associative memory determined from m reference patterns, the experiments showed that P_max(G(W,Θ)) is of order O( mn) and T_ord(GB(W,Θ))=2 when m =1 or 2, for all n⩾3, where n is the size of the net and Θ is zero factor