An information-based neural approach to generic constraint satisfaction

Henrik Jönsson, Bo Söderberg

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskriftPeer review

3 Citeringar (SciVal)

Sammanfattning

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.
Originalspråkengelska
Sidor (från-till)1-17
TidskriftArtificial Intelligence
Volym142
Utgåva1
DOI
StatusPublished - 2002

Ämnesklassifikation (UKÄ)

  • Biofysik

Fingeravtryck

Utforska forskningsämnen för ”An information-based neural approach to generic constraint satisfaction”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här