An Explicitly Relational Neural Network Architecture
This work addresses the challenge of integrating relational reasoning into neural networks for AI researchers, though it appears incremental as it builds on existing methods for specific tasks.
The authors tackled the problem of bridging deep learning and symbolic AI by developing a neural network architecture that learns explicitly relational representations from raw pixels, and demonstrated that pre-training on a curriculum of visual relational reasoning tasks enables better transfer to unseen tasks compared to baseline architectures.
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.