(2021) Teaching Temporal Logics to Neural Networks.
|
Text
Teaching Temporal Logics to Neural Networks.pdf Download (1MB) | Preview |
Abstract
We study two fundamental questions in neuro-symbolic computing: can deep learning tackle challenging problems in logics end-to-end, and can neural networks learn the semantics of logics. In this work we focus on linear-time temporal logic (LTL), as it is widely used in verification. We train a Transformer on the problem to directly predict a solution, i.e. a trace, to a given LTL formula. The training data is generated with classical solvers, which, however, only provide one of many possible solutions to each formula. We demonstrate that it is sufficient to train on those particular solutions to formulas, and that Transformers can predict solutions even to formulas from benchmarks from the literature on which the classical solver timed out. Transformers also generalize to the semantics of the logics: while they often deviate from the solutions found by the classical solvers, they still predict correct solutions to most formulas.
| Item Type: | Conference or Workshop Item (A Paper) (Paper) |
|---|---|
| Divisions: | Bernd Finkbeiner (Reactive Systems Group, RSG) |
| Conference: | ICLR International Conference on Learning Representations |
| Depositing User: | Frederik Schmitt |
| Date Deposited: | 06 May 2022 07:01 |
| Last Modified: | 06 May 2022 07:01 |
| Primary Research Area: | NRA2: Reliable Security Guarantees |
| URI: | https://publications.cispa.saarland/id/eprint/3656 |
Actions
Actions (login required)
 |
View Item |