A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)

Abstract

Hyperdimensional (HD) computing is a set of neurally inspired methods for computing on high-dimensional, 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. We present a novel mathematical framework that unifies analysis of HD computing architectures, and provides general, non-asymptotic, sufficient conditions under which HD information processing techniques will succeed.

Cite

Text

Thomas et al. "A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/808

Markdown

[Thomas et al. "A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/thomas2022ijcai-theoretical/) doi:10.24963/IJCAI.2022/808

BibTeX

@inproceedings{thomas2022ijcai-theoretical,
  title     = {{A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)}},
  author    = {Thomas, Anthony and Dasgupta, Sanjoy and Rosing, Tajana},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {5772-5776},
  doi       = {10.24963/IJCAI.2022/808},
  url       = {https://mlanthology.org/ijcai/2022/thomas2022ijcai-theoretical/}
}