THDC: Training Hyperdimensional Computing Models with Backpropagation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 6 of its 17 references that are in the map. First posted on arXiv 27 Jan 2026.
Builds on
6 of 17 references.
References · 6
- 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 98
- 2022LeHDC: Learning-Based Hyperdimensional Computing Classifiercited by 17
- 2021Hypervector Design for Efficient Hyperdimensional Computing on Edge Devicescited by 16
- 2022A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devicescited by 11
- 2022Hyperdimensional Computing vs. Neural Networks: Comparing Architecture and Learning Processcited by 7
- 2023Efficient Hyperdimensional Computingcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.