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 language | English (US) |
---|---|
Pages (from-to) | 287-292 |
Number of pages | 6 |
Journal | Parallel Computing |
Volume | 16 |
Issue number | 2-3 |
DOIs | |
State | Published - Dec 1990 |
Keywords
- Combinatorial optimization
- Connectionism
- High-order weights
- Hopfield and Tank networks
- Neural networks
- Simulated annealing
- Triangle partitioning