Cognitive Computation

, Volume 1, Issue 2, pp 139–159

Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors

Article

DOI: 10.1007/s12559-009-9009-8

Cite this article as:
Kanerva, P. Cogn Comput (2009) 1: 139. doi:10.1007/s12559-009-9009-8

Abstract

The 1990s saw the emergence of cognitive models that depend on very high dimensionality and randomness. They include Holographic Reduced Representations, Spatter Code, Semantic Vectors, Latent Semantic Analysis, Context-Dependent Thinning, and Vector-Symbolic Architecture. They represent things in high-dimensional vectors that are manipulated by operations that produce new high-dimensional vectors in the style of traditional computing, in what is called here hyperdimensional computing on account of the very high dimensionality. The paper presents the main ideas behind these models, written as a tutorial essay in hopes of making the ideas accessible and even provocative. A sketch of how we have arrived at these models, with references and pointers to further reading, is given at the end. The thesis of the paper is that hyperdimensional representation has much to offer to students of cognitive science, theoretical neuroscience, computer science and engineering, and mathematics.

Keywords

Holographic reduced representation Holistic record Holistic mapping Random indexing Cognitive code von Neumann architecture 

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Center for the Study of Language and InformationStanford UniversityStanfordUSA

Personalised recommendations