Year: 2026
Type: conference-paper
Abstract: Hyperdimensional computing (HDC) offers lightweight learning for energy-constrained devices by encoding data into high-dimensional vectors.However, its reliance on ultra-high dimensionality and static, randomly initialized hypervectors limits memory efficiency and learning capacity.Therefore, we propose Trainable Hyperdimensional Computing (THDC), which enables end-to-end HDC via backpropagation.THDC replaces randomly initialized vectors with trainable embeddings and introduces a one-layer binary neural network to optimize class representations.Evaluated on MNIST, Fashion-MNIST and CIFAR-10, THDC achieves equal or better accuracy than state-of-the-art HDC, with dimensionality reduced from 10.000 to 64.
Authors: Hanne Dejonghe, Sam Leroux
Institutions: Ghent University, IMEC
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7154617490
