Relational knowledge is a hallmark of human cognition and the subject of a vast body of research. In this paper we argue that existing accounts of relations are inadequate because they have little to say about how relations arise in the first place and because they tend to be limited to particular sorts of relational tasks. We present a new approach to the learning and representation of relations, an approach that makes use of what we call micro-relation units (MRUs). Each MRU represents a relation between features of different objects rather than between objects themselves. We show how this approach offers an account of the grounding of relations, and we describe a neural-network implementation of the MRU framework and show how it enables a variety of relational tasks to be performed by the same system.
Download a PostScript version