Defining neurosymbolic AI

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: De Smet, Lennert, De Raedt, Luc
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908450413346816
author De Smet, Lennert
De Raedt, Luc
author_facet De Smet, Lennert
De Raedt, Luc
contents Neurosymbolic AI focuses on integrating learning and reasoning, in particular, on unifying logical and neural representations. Despite the existence of an alphabet soup of neurosymbolic AI systems, the field is lacking a generally accepted formal definition of what neurosymbolic models and inference really are. We introduce a formal definition for neurosymbolic AI that makes abstraction of its key ingredients. More specifically, we define neurosymbolic inference as the computation of an integral over a product of a logical and a belief function. We show that our neurosymbolic AI definition makes abstraction of key representative neurosymbolic AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11127
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Defining neurosymbolic AI
De Smet, Lennert
De Raedt, Luc
Artificial Intelligence
Neurosymbolic AI focuses on integrating learning and reasoning, in particular, on unifying logical and neural representations. Despite the existence of an alphabet soup of neurosymbolic AI systems, the field is lacking a generally accepted formal definition of what neurosymbolic models and inference really are. We introduce a formal definition for neurosymbolic AI that makes abstraction of its key ingredients. More specifically, we define neurosymbolic inference as the computation of an integral over a product of a logical and a belief function. We show that our neurosymbolic AI definition makes abstraction of key representative neurosymbolic AI systems.
title Defining neurosymbolic AI
topic Artificial Intelligence
url https://arxiv.org/abs/2507.11127