Code for Diff-ASP-Propagators for Differentiable Answer Set Programming and Differentiable SAT, using Python and Clingo's propagators. Proof-of-concept only; for a realistic approach to Differentiable Satisfiability and Differentiable ASP (including Probabilistic Answer Set Programming and Probabilistic Satisfiability Solving), see Diff-SAT https://github.com/MatthiasNickles/diff-SAT
For details on this approach, see http://ceur-ws.org/Vol-2219/paper7.pdf
Publications:
- Matthias Nickles: Differentiable SAT/ASP. In Proceedings of the 5th International Workshop on Probabilistic Logic Programming (PLP'18), CEUR 2018.
- Matthias Nickles: Sampling-Based SAT/ASP Multi-Model Optimization as a Framework for Probabilistic Inference. Proceedings of the 28th International Conference on Inductive Logic Programming (ILP'18). Lecture Notes in Artificial Intelligence (LNAI), Springer, 2018.
- Matthias Nickles: Distribution-Aware Sampling of Answer Sets. Proceedings of the 12th International Conference on Scalable Uncertainty Management (SUM'18). Lecture Notes in Artificial Intelligence (LNAI), Springer, 2018.