Learning holistic transformation of HRR from examples

Holographic Reduced Representation is a representational scheme which allows for the representation of variable-sized structures in a distributed manner. It has been shown that these structures can be transformed holistically. However, in order to do so, the transformation vector was constructed by hand. In this paper we show that a simple gradient descent approach can be used to learn the holistic transformations of Holographic Reduced Representations from examples. The acquired knowledge can be generalised to structures containing unseen elements and to structures more complex than the training examples.