Hopfield Neural Networks and Self-Stabilization

This paper studies Hopfield neural networks from the perspective of self-stabilizing distributed computation. Known self-stabilization results on Hopfield networks are surveyed. Key ingredients of the proofs are given. Novel applications of self-stabilization—associative memories and optimization—arising from the context of neural networks are discussed. Two new results at the intersection of Hopfield nets and of distributed systems are obtained: One involves convergence under a fine-grained implementation; the other is on perturbation analysis. Some possibilities for further research at the intersection of these two fields are discussed.