Temporal logics and their automata-based counterparts have risen as languages for reasoning about processes and verifying their properties. Increasingly, though, the events in a process refer to observations perceived and classified by a neural network, calling for a mixed formalism capable of dealing with the uncertainty of these classifications. We propose Deep Weighted Finite Automata, a new neuro-symbolic architecture combining formal temporal specifications and neural classifications. We also show how to make probabilistic inferences and compute the most likely execution given a sequence of perceptions.
Casone, F., Penaloza, R. (2026). Deep Weighted Finite Automata. In Proceedings of the Joint Workshop on Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs (SKILLED-LLMs 2026) co-located with the Federated Logic Conference 2026 (FLoC 2026) (pp.74-87). CEUR-WS.
Deep Weighted Finite Automata
Penaloza R.
2026
Abstract
Temporal logics and their automata-based counterparts have risen as languages for reasoning about processes and verifying their properties. Increasingly, though, the events in a process refer to observations perceived and classified by a neural network, calling for a mixed formalism capable of dealing with the uncertainty of these classifications. We propose Deep Weighted Finite Automata, a new neuro-symbolic architecture combining formal temporal specifications and neural classifications. We also show how to make probabilistic inferences and compute the most likely execution given a sequence of perceptions.
| File | Dimensione | Formato | |
|---|---|---|---|
|
Casone-Penaloza-2026-SKILLED-LLMs-CEUR-VoR.pdf
accesso aperto
Tipologia di allegato:
Publisher’s Version (Version of Record, VoR)
Licenza:
Creative Commons
Dimensione
184.07 kB
Formato
Adobe PDF
|
184.07 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
