High-order Hopfield and Tank optimization networks

Tariq Samad, Paul Harper

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

We employ high-order weights to extend the class of optimization problems that can be solved with neural networks. Hopfield and Tank networks are used; the associated energy function is a polynomial with order equal to the highest order weights in the network. As an example, we consider the problem of partitioning a graph into triangles. Simulation results indicate that multiple runs on a problem can be considered independent trials; high performance can thereby be achiebed feasibly.

Original languageEnglish (US)
Pages (from-to)287-292
Number of pages6
JournalParallel Computing
Volume16
Issue number2-3
DOIs
StatePublished - Dec 1990

Keywords

  • Combinatorial optimization
  • Connectionism
  • High-order weights
  • Hopfield and Tank networks
  • Neural networks
  • Simulated annealing
  • Triangle partitioning

Fingerprint

Dive into the research topics of 'High-order Hopfield and Tank optimization networks'. Together they form a unique fingerprint.

Cite this