Critical analysis of applying Hopfield neural net model to optimization problems

摘要

The authors present a rigorous matrix-based analysis of the Hopfield model in order to understand the fundamental characteristics of the model, its strengths, and its weaknesses. They formally show why the results obtained by applying the Hopfield model to most NP-complete problems are in general unsatisfactory. They also indicate that promising results are achieved randomly. Possible amendments and future research directions are discussed.