Timezone: »

 
Poster
An Explicitly Relational Neural Network Architecture
Murray Shanahan · Kyriacos Nikiforou · Antonia Creswell · Christos Kaplanis · David GT Barrett · Marta Garnelo

Tue Jul 14 01:00 PM -- 01:45 PM & Wed Jul 15 01:00 AM -- 01:45 AM (PDT) @
in Poster Session 7 »

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: Architectures · Representation Learning · Deep Learning - General

Author Information

Murray Shanahan (DeepMind / Imperial College London)
Kyriacos Nikiforou (DeepMind)
Antonia Creswell (Deep Mind)
Christos Kaplanis (DeepMind Technologies Ltd)
David GT Barrett (DeepMind)
Marta Garnelo (DeepMind)

More from the Same Authors