Defining neurosymbolic AI
This provides a foundational framework for researchers in neurosymbolic AI, though it is incremental as it formalizes existing concepts rather than introducing new methods.
The paper tackles the lack of a formal definition for neurosymbolic AI by introducing a definition that abstracts key ingredients, specifically defining neurosymbolic inference as an integral over a product of logical and belief functions, and shows it applies to representative systems.
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.