An Information-Based Neural Approach to Constraint Satisfaction
| dc.creator | Jonsson, Henrik | |
| dc.creator | Soderberg, Bo | |
| dc.date | 2001-05-16 | |
| dc.date.accessioned | 2026-07-07T02:41:26Z | |
| dc.date.available | 2026-07-07T02:41:26Z | |
| dc.description | A novel artificial neural network approach to constraint satisfaction problems is presented. Based on information-theoretical considerations, it differs from a conventional mean-field approach in the form of the resulting free energy. The method, implemented as an annealing algorithm, is numerically explored on a testbed of K-SAT problems. The performance shows a dramatic improvement to that of a conventional mean-field approach, and is comparable to that of a state-of-the-art dedicated heuristic (Gsat+Walk). The real strength of the method, however, lies in its generality -- with minor modifications it is applicable to arbitrary types of discrete constraint satisfaction problems. | |
| dc.description | 13 pages, 3 figures,(to appear in Neural Computation) | |
| dc.identifier | https://arxiv.org/abs/cond-mat/0105319 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/0105319 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/17743 | |
| dc.subject | Disordered Systems and Neural Networks | |
| dc.title | An Information-Based Neural Approach to Constraint Satisfaction | |
| dc.type | text |