Neural logic programs and neural nets
arXiv:2406.11888v12 citations
Originality Incremental advance
AI Analysis
This work addresses the challenge of combining subsymbolic and symbolic AI for researchers in neural-symbolic integration, presenting a foundational equivalence.
The paper tackles the integration of neural networks and symbolic logic by defining answer set semantics for boolean neural nets and introducing neural logic programs, showing their equivalence.
Neural-symbolic integration aims to combine the connectionist subsymbolic with the logical symbolic approach to artificial intelligence. In this paper, we first define the answer set semantics of (boolean) neural nets and then introduce from first principles a class of neural logic programs and show that nets and programs are equivalent.