A Theoretical Perspective on Hyperdimensional Computing

TL;DR

This paper provides a comprehensive theoretical overview of hyperdimensional computing, emphasizing its potential for energy-efficient, noise-robust learning through high-dimensional representations and simple algorithms.

Contribution

It offers a unified theoretical framework for understanding hyperdimensional computing's suitability for learning tasks.

Findings

HD computing offers energy-efficient and noise-robust data representations

Theoretical analysis clarifies the suitability of HD representations for learning

Unified treatment enhances understanding of HD computational principles

Abstract

Hyperdimensional (HD) computing is a set of neurally inspired methods for obtaining 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. 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.