XL-HD: Extended Learning in Hyperdimensional Computing via Deterministic Projections for In-Memory Accelerators

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Moon, Sabrina Hassan, Masum, Abu Kaisar Mohammad, Aygun, Sercan, Reis, Dayane
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911713746485248
author Moon, Sabrina Hassan
Masum, Abu Kaisar Mohammad
Aygun, Sercan
Reis, Dayane
author_facet Moon, Sabrina Hassan
Masum, Abu Kaisar Mohammad
Aygun, Sercan
Reis, Dayane
contents Hyperdimensional computing (HDC) is a promising approach for energy-efficient edge machine learning (ML), where low latency, low power, and tight memory budgets are essential. However, traditional HDC relies on symbolic binding and pseudo-random high-dimensional vectors, which require large dimensionality and heuristic updates to reach competitive accuracy, limiting deployment on edge hardware. We introduce XL-HD, a deterministic, projection-based, fully learnable HDC framework tailored for in-memory acceleration within edge computing systems. The method uses a fixed Sobol sequence to project binary inputs, extending learning beyond conventional HDC. During training, class prototypes are optimized in real-valued space and later binarized, enabling an entirely binary dot-product inference pipeline ideal for IMC hardware such as ReRAM crossbars. XL-HD achieves competitive accuracy on MNIST, UCIHAR, and ISOLET while maintaining a compact IMC-based inference engine with $0.395 \ \text{mm}^2$ area and only $0.40 \ μ\text{J}$ per single-cycle inference.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24788
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle XL-HD: Extended Learning in Hyperdimensional Computing via Deterministic Projections for In-Memory Accelerators
Moon, Sabrina Hassan
Masum, Abu Kaisar Mohammad
Aygun, Sercan
Reis, Dayane
Hardware Architecture
Emerging Technologies
Hyperdimensional computing (HDC) is a promising approach for energy-efficient edge machine learning (ML), where low latency, low power, and tight memory budgets are essential. However, traditional HDC relies on symbolic binding and pseudo-random high-dimensional vectors, which require large dimensionality and heuristic updates to reach competitive accuracy, limiting deployment on edge hardware. We introduce XL-HD, a deterministic, projection-based, fully learnable HDC framework tailored for in-memory acceleration within edge computing systems. The method uses a fixed Sobol sequence to project binary inputs, extending learning beyond conventional HDC. During training, class prototypes are optimized in real-valued space and later binarized, enabling an entirely binary dot-product inference pipeline ideal for IMC hardware such as ReRAM crossbars. XL-HD achieves competitive accuracy on MNIST, UCIHAR, and ISOLET while maintaining a compact IMC-based inference engine with $0.395 \ \text{mm}^2$ area and only $0.40 \ μ\text{J}$ per single-cycle inference.
title XL-HD: Extended Learning in Hyperdimensional Computing via Deterministic Projections for In-Memory Accelerators
topic Hardware Architecture
Emerging Technologies
url https://arxiv.org/abs/2605.24788