Neural logic programs and neural nets

TL;DR

This paper explores the integration of neural networks with logical programming by defining answer set semantics for neural nets and introducing neural logic programs, establishing their equivalence.

Contribution

It introduces a formal framework linking neural networks and logic programs through answer set semantics, advancing neural-symbolic integration.

Findings

Neural networks can be given answer set semantics.

Neural logic programs are equivalent to neural networks.

Framework bridges connectionist and symbolic AI.

Abstract

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.