NeSyA: Neurosymbolic Automata

Neurosymbolic Artificial Intelligence (NeSy) has emerged as a promising direction to integrate low level perception with high level reasoning. Unfortunately, little attention has been given to developing NeSy systems tailored to temporal/sequential problems. This entails reasoning symbolically over...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-12
Main Authors: Manginas, Nikolaos, Paliouras, George, De Raedt, Luc
Format: Article
Language:English
Subjects:
Artificial intelligence
Automata theory
Low level
Reasoning
Semantics
Sequences
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neurosymbolic Artificial Intelligence (NeSy) has emerged as a promising direction to integrate low level perception with high level reasoning. Unfortunately, little attention has been given to developing NeSy systems tailored to temporal/sequential problems. This entails reasoning symbolically over sequences of subsymbolic observations towards a target prediction. We show that using a probabilistic semantics symbolic automata, which combine the power of automata for temporal structure specification with that of propositional logic, can be used to reason efficiently and differentiably over subsymbolic sequences. The proposed system, which we call NeSyA (Neuro Symbolic Automata), is shown to either scale or perform better than existing NeSy approaches when applied to problems with a temporal component.
ISSN:2331-8422