English

An Explicitly Relational Neural Network Architecture

Machine Learning 2020-06-24 v4 Machine Learning

Abstract

With a view to bridging the gap between deep learning and symbolic AI, we present a novel end-to-end neural network architecture that learns to form propositional representations with an explicitly relational structure from raw pixel data. In order to evaluate and analyse the architecture, we introduce a family of simple visual relational reasoning tasks of varying complexity. We show that the proposed architecture, when pre-trained on a curriculum of such tasks, learns to generate reusable representations that better facilitate subsequent learning on previously unseen tasks when compared to a number of baseline architectures. The workings of a successfully trained model are visualised to shed some light on how the architecture functions.

Keywords

Cite

@article{arxiv.1905.10307,
  title  = {An Explicitly Relational Neural Network Architecture},
  author = {Murray Shanahan and Kyriacos Nikiforou and Antonia Creswell and Christos Kaplanis and David Barrett and Marta Garnelo},
  journal= {arXiv preprint arXiv:1905.10307},
  year   = {2020}
}

Comments

In Proceedings ICML 2020

R2 v1 2026-06-23T09:22:39.604Z