On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hopfield Networks With Self-Interaction Neurons

摘要

In this paper, a discrete-time convergence the- orem for continuous-state Hopfield networks with self-interaction neurons is proposed. This theorem differs from the previous work by Wang in that the original updating rule is maintained while the network is still guaranteed to monotonically decrease to a sta- ble state. The relationship between the parameters in a typical class of energy functions is also investigated, and consequently a "guided trial-and-error" technique is proposed to determine the parameter values. The third problem discussed in this paper is the post-processing of outputs, which turns out to be rather important even though it never attracts enough attention.