Answers are grounded in this paper and cite their sources.
A complex-valued Hopfield neural network (CHNN) is a model of a Hopfield neural network using multistate neurons. The stability conditions of CHNNs have been widely studied. A CHNN with a synchronous mode will converge to a fixed point or a cycle of length 2. A rotor Hopfield neural network (RHNN) is also a model of a multistate Hopfield neural network. RHNNs have much higher storage capacity and noise tolerance than CHNNs. We extend the theories regarding the stability of CHNNs to RHNNs. In addition, we investigate the stability of RHNNs with the projection rule. Although a CHNN with projection rule can be trapped at a cycle, an RHNN with projection rule converges to a fixed point. This is one of the great advantages of RHNNs.
No takes yet. Share an insight, caveat, or question.
Masaki Kobayashi (2016) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: