A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)

Anthony Thomas; Sanjoy Dasgupta; Tajana Rosing

IJCAI 2022poster0 citations

A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)

Anthony Thomas, Sanjoy Dasgupta, Tajana Rosing

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.

Machine Learning: Symbolic methodsKnowledge Representation and Reasoning: Knowledge Representation LanguagesKnowledge Representation and Reasoning: Learning and reasoning

BibTeX

@inproceedings{ijcai2022p808,
  title     = {A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract)},
  author    = {Thomas, Anthony and Dasgupta, Sanjoy and Rosing, Tajana},
  booktitle = {Proceedings of the Thirty-First International Joint Conference on
               Artificial Intelligence, {IJCAI-22}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Lud De Raedt},
  pages     = {5772--5776},
  year      = {2022},
  month     = {7},
  note      = {Journal Track},
  doi       = {10.24963/ijcai.2022/808},
  url       = {https://doi.org/10.24963/ijcai.2022/808},
}