A Theoretical Perspective on Hyperdimensional Computing
This is a theoretical review that synthesizes existing knowledge for researchers in computer hardware and machine learning interested in energy-efficient computing methods.
The paper reviews the theoretical foundations of hyperdimensional computing, focusing on how high-dimensional, low-precision representations enable energy-efficient and noise-robust learning tasks, without presenting new experimental results or numbers.
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.