Recursive neural networks with high capacity
C.-J. Chen, John Y. Cheung · 2002
square root 3/sup n-1/ is derived as the lower bound of maximum capacity in n-neuron recursive neural networks. It is shown that if n to infinity , the number of stable vectors of (n+1)-neuron net is two times that of n-neuron net and the number of stable vectors of n-neuron net is C2/sup n/ with 0>