An Explicitly Relational Neural Network Architecture

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

Keywords: [ Architectures ] [ Representation Learning ] [ Deep Learning - General ]

[ Abstract ]
Tue 14 Jul 1 p.m. PDT — 1:45 p.m. PDT
Wed 15 Jul 1 a.m. PDT — 1:45 a.m. PDT


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.

Chat is not available.