AILGMLApr 26, 2019

Neural Logic Machines

arXiv:1904.11694v1296 citations
Originality Highly original
AI Analysis

This addresses the problem of integrating symbolic and neural approaches for AI, enabling robust performance on tasks that are difficult for either method alone.

The authors tackled the challenge of combining neural networks and logic programming for inductive learning and reasoning, achieving perfect generalization on tasks like sorting arrays and relational reasoning.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes