Estimating analogical similarity by dot-products of Holographic Reduced Representations

Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)

Bibtex Metadata Paper


Tony A. Plate


Models of analog retrieval require a computationally cheap method of estimating similarity between a probe and the candidates in a large pool of memory items. The vector dot-product operation would be ideal for this purpose if it were possible to encode complex structures as vector representations in such a way that the superficial similarity of vector representations reflected underlying structural similarity. This paper de(cid:173) scribes how such an encoding is provided by Holographic Reduced Rep(cid:173) resentations (HRRs), which are a method for encoding nested relational structures as fixed-width distributed representations. The conditions un(cid:173) der which structural similarity is reflected in the dot-product rankings of HRRs are discussed.