On the capacity of ternary Hebbian networks
Yoram Baram · IEEE Transactions on Information Theory · 1991
Networks of ternary neurons storing random vectors over the set (-1,0,1) by the so-called Hebbian rule are considered. It is shown that the maximal number of stored patterns that are equilibrium states of the network with probability tending to one as N tends to infinity is at least on the order of N/sup 2-1// alpha /K, where N is the number of neurons, K is the number of nonzero elements in a pattern. and t= alpha K, 1/2>