A Theoretical Perspective on Hyperdimensional Computing

Abstract

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining highdimensional, low-precision, distributed representations of data. These representations can be combined with simple, neurally plausible algorithms to effect a variety of information processing tasks. HD computing has recently garnered significant interest from the computer hardware community as an energy-efficient, low-latency, and noise-robust tool for solving learning problems. In this review, we present a unified treatment of the theoretical foundations of HD computing with a focus on the suitability of representations for learning.

Cite

Text

Thomas et al. "A Theoretical Perspective on Hyperdimensional Computing." Journal of Artificial Intelligence Research, 2021. doi:10.1613/JAIR.1.12664

Markdown

[Thomas et al. "A Theoretical Perspective on Hyperdimensional Computing." Journal of Artificial Intelligence Research, 2021.](https://mlanthology.org/jair/2021/thomas2021jair-theoretical/) doi:10.1613/JAIR.1.12664

BibTeX

@article{thomas2021jair-theoretical,
  title     = {{A Theoretical Perspective on Hyperdimensional Computing}},
  author    = {Thomas, Anthony and Dasgupta, Sanjoy and Rosing, Tajana},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2021},
  pages     = {215-249},
  doi       = {10.1613/JAIR.1.12664},
  volume    = {72},
  url       = {https://mlanthology.org/jair/2021/thomas2021jair-theoretical/}
}