A simple neural network module for relational reasoning

NeurIPS 2017 Adam SantoroDavid RaposoDavid G. T. BarrettMateusz MalinowskiRazvan PascanuPeter BattagliaTimothy Lillicrap

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.