Statistical Prediction with Kanerva's Sparse Distributed Memory

NeurIPS 1988 pp. 586-593

/neurips/1988/rogers1988neurips-statistical/

Abstract

A new viewpoint of the processing performed by Kanerva's sparse distributed memory (SDM) is presented. In conditions of near- or over- capacity, where the associative-memory behavior of the mod(cid:173) el breaks down, the processing performed by the model can be inter(cid:173) preted as that of a statistical predictor. Mathematical results are presented which serve as the framework for a new statistical view(cid:173) point of sparse distributed memory and for which the standard for(cid:173) mulation of SDM is a special case. This viewpoint suggests possi(cid:173) ble enhancements to the SDM model, including a procedure for improving the predictiveness of the system based on Holland's work with 'Genetic Algorithms', and a method for improving the capacity of SDM even when used as an associative memory.

PDF NeurIPS Semantic Scholar

Cite

Text

Rogers. "Statistical Prediction with Kanerva's Sparse Distributed Memory." Neural Information Processing Systems, 1988.

Markdown

[Rogers. "Statistical Prediction with Kanerva's Sparse Distributed Memory." Neural Information Processing Systems, 1988.](https://mlanthology.org/neurips/1988/rogers1988neurips-statistical/)

BibTeX

@inproceedings{rogers1988neurips-statistical,
  title     = {{Statistical Prediction with Kanerva's Sparse Distributed Memory}},
  author    = {Rogers, David},
  booktitle = {Neural Information Processing Systems},
  year      = {1988},
  pages     = {586-593},
  url       = {https://mlanthology.org/neurips/1988/rogers1988neurips-statistical/}
}