ML Anthology

Estimating Analogical Similarity by Dot-Products of Holographic Reduced Representations

Tony A. Plate
NeurIPS 1993 pp. 1109-1116
/neurips/1993/plate1993neurips-estimating/

Abstract

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.

PDF NeurIPS Semantic Scholar

Cite

Text

Plate. "Estimating Analogical Similarity by Dot-Products of Holographic Reduced Representations." Neural Information Processing Systems, 1993.

Markdown

[Plate. "Estimating Analogical Similarity by Dot-Products of Holographic Reduced Representations." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/plate1993neurips-estimating/)

BibTeX

@inproceedings{plate1993neurips-estimating,
  title     = {{Estimating Analogical Similarity by Dot-Products of Holographic Reduced Representations}},
  author    = {Plate, Tony A.},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {1109-1116},
  url       = {https://mlanthology.org/neurips/1993/plate1993neurips-estimating/}
}