Neural Logic Machines

TL;DR

The Neural Logic Machine (NLM) combines neural networks and logic programming to enable inductive learning and reasoning, achieving perfect generalization on various relational and decision-making tasks.

Contribution

NLM introduces a neural-symbolic architecture that effectively integrates neural approximation with symbolic logic reasoning for complex tasks.

Findings

NLM achieves perfect generalization on relational reasoning tasks.

NLM successfully handles large-scale sorting and pathfinding tasks.

NLM outperforms neural networks and logic programming alone.

Abstract

We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifiers. After being trained on small-scale tasks (such as sorting short arrays), NLMs can recover lifted rules, and generalize to large-scale tasks (such as sorting longer arrays). In our experiments, NLMs achieve perfect generalization in a number of tasks, from relational reasoning tasks on the family tree and general graphs, to decision making tasks including sorting arrays, finding shortest paths, and playing the blocks world. Most of these tasks are hard to accomplish for neural networks or inductive logic programming alone.