# THDC: Training Hyperdimensional Computing Models with Backpropagation

arXiv: https://arxiv.org/abs/2602.00116 · HTML: https://mlsanity.com/paper/2602.00116/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 6 of 6)

- [A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations](https://mlsanity.com/paper/2111.06077/) (2021)
- [LeHDC: Learning-Based Hyperdimensional Computing Classifier](https://mlsanity.com/paper/2203.09680/) (2022)
- [Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices](https://mlsanity.com/paper/2103.06709/) (2021)
- [A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices](https://mlsanity.com/paper/2203.04894/) (2022)
- [Hyperdimensional Computing vs. Neural Networks: Comparing Architecture and Learning Process](https://mlsanity.com/paper/2207.12932/) (2022)
- [Efficient Hyperdimensional Computing](https://mlsanity.com/paper/2301.10902/) (2023)

## Built on by (most cited first, 1 of 1)

- [Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning](https://mlsanity.com/paper/2610.10630/) (2026)

## 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.