On the distributed parallel simulation of Hopefield's neural networks
Software—Practice & Experience
Logical inference in symmetric connectionist networks
Logical inference in symmetric connectionist networks
SATyrus: A SAT-based Neuro-Symbolic Architecture for Constraint Processing
HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
Machine Learning
Generalizing Boolean satisfiability I: background and survey of existing work
Journal of Artificial Intelligence Research
Mapping and combining combinatorial problems into energy landscapes via pseudo-boolean constraints
BVAI'05 Proceedings of the First international conference on Brain, Vision, and Artificial Intelligence
Hi-index | 0.00 |
This paper presents the implementation of ARQ-PROP II, a limited-depth propositional reasoner, via the compilation of its specification into an exact formulation using the satyrus platform. satyrus' compiler takes as input the definition of a problem as a set of pseudo-Boolean constraints and produces, as output, the Energy function of a higher-order artificial neural network. This way, satisfiability of a formula can be associated to global optima. In the case of ARQ-PROP II, global optima is associated to Resolution-based refutation, in such a way that allows for simplified abduction and prediction to be unified with deduction. Besides experimental results on deduction with ARQ-PROP II, this work also corrects the mapping of satisfiability into Energy minima originally proposed by Gadi Pinkas.