Abstract
A novel artificial neural network heuristic (INN) for general constraint satisfaction problems is presented. extending a recently suggested method restricted to boolean variables. In contrast to conventional ANN methods, it employs a particular type of non-polynomial cost function, based on the information balance between variables and constraints in a mean-field setting. Implemented as an annealing algorithm, the method is numerically explored on a testbed of Graph Coloring problems. The performance is comparable to that of dedicated heuristics, and clearly superior to that of conventional mean-field annealing.
Original language | English |
---|---|
Pages (from-to) | 1-17 |
Journal | Artificial Intelligence |
Volume | 142 |
Issue number | 1 |
DOIs | |
Publication status | Published - 2002 |
Subject classification (UKÄ)
- Biophysics
Free keywords
- constraint satisfaction
- connectionist
- artificial
- neural network
- heuristic information
- mean-field annealing
- graph coloring