An information-based neural approach to generic constraint satisfaction

Henrik Jönsson, Bo Söderberg
2002 Artificial Intelligence  
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
more » ... mance is comparable to that of dedicated heuristics, and clearly superior to that of conventional mean-field annealing.
doi:10.1016/s0004-3702(02)00291-6 fatcat:x42fipv66bhwxbpl54sc5dwqna