Learning from Hypervectors: A Survey on Hyperdimensional Encoding
Open Access
- 19 November 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
Abstract
Hyperdimensional computing (HDC) is an emerging computing paradigm that imitates the brain’s structure to offer a powerful and efficient processing and learning model. In HDC, the data are encoded with long vectors, called hypervectors , which typically range from 1, 000 to 10, 000 in length. The literature provides several encoding methods to generate orthogonal or correlated hypervectors, based on the application. Existing surveys focus on overall HDC system aspects like inputs, primary computations, and outputs. However, this study takes a more specific approach. It zeroes in on the HDC system input and the generation of hypervectors, directly influencing the hypervector encoding. This survey brings together various hypervector generation and encoding methods, exploring the limitations, challenges, and potential benefits they entail.This publication has 161 references indexed in Scilit:
- DystoHD: an area-efficient hyperdimensional computing system with dynamic hypervector generation for memory-constrained devicesThe Journal of Supercomputing, 2026
- Classification using hyperdimensional computing: a review with comparative analysisArtificial Intelligence Review, 2025
- HyperSense: Hyperdimensional Intelligent Sensing for Energy‐Efficient Sparse Data ProcessingAdvanced Intelligent Systems, 2024
- Self‐selective memristor‐enabled in‐memory search for highly efficient data miningInfoMat, 2023
- A comparison of vector symbolic architecturesArtificial Intelligence Review, 2021
- Question Answering for Visual Navigation in Human-Centered Environments2021
- Hyperdimensional Computing with Learnable Projection for User Adaptation Framework2021
- Adversarial Attacks on Voice Recognition Based on Hyper Dimensional ComputingJournal of Signal Processing Systems, 2021
- Task-Projected Hyperdimensional Computing for Multi-task Learning2020
- Hyperdimensional Computing for Blind and One-Shot Classification of EEG Error-Related PotentialsMobile Networks and Applications, 2017