An Explicitly Relational Neural Network Architecture

Murray Shanahan, Kyriacos Nikiforou, Antonia Creswell, Christos Kaplanis, David Barrett, Marta Garnelo

Keywords: relational representation

TL;DR: We present an end-to-end differentiable architecture that learns to map pixels to predicates, and evaluate it on a suite of simple relational reasoning tasks

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.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:1905.10307/code)