Published by MIT Press. Copyright 1999 Massachusetts Institute of Technology.

Your institution may already be a subscriber to CJTCS. If not, please subscribe.

Abstract

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.

• Preformatted versions of the article
  • DVI (75,868 bytes)
  • PostScript (313,068 bytes)
  • PDF (286,454 bytes)
  • Audio by AsTeR (to appear)
• Source materials for custom formatting
  • LaTeX (cj99-06.tex, 50,565 bytes)
  • BIBTeX (cj99-06.bib, 10,737 bytes)
  • Parameter settings for custom formatting (cjropts.tex, 165 bytes)
  • Self citation in BIBTeX (292 bytes)
• Online discussion
• Instructions for Readers

DOI: 10.4086/cjtcs.1999.006

---

Article 5 Article 7
Volume 1999 Published articles

Last modified: Sat Mar 20 09:32:31 CST 1999