# DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computing

arXiv: https://arxiv.org/abs/2411.10692 · HTML: https://mlsanity.com/paper/2411.10692/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 61 references that are in the map.
- First posted on arXiv 16 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [Selection via Proxy: Efficient Data Selection for Deep Learning](https://mlsanity.com/paper/1906.11829/) (2019)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Learning how to explain neural networks: PatternNet and PatternAttribution](https://mlsanity.com/paper/1705.05598/) (2017)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations](https://mlsanity.com/paper/2106.12723/) (2021)
- [Model Assertions for Monitoring and Improving ML Models](https://mlsanity.com/paper/2003.01668/) (2020)
- [Torchhd: An Open Source Python Library to Support Research on Hyperdimensional Computing and Vector Symbolic Architectures](https://mlsanity.com/paper/2205.09208/) (2022)
- [DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification](https://mlsanity.com/paper/2304.05503/) (2023)
- [Characterizing and Taming Model Instability Across Edge Devices](https://mlsanity.com/paper/2010.09028/) (2020)
- [ML-EXray: Visibility into ML Deployment on the Edge](https://mlsanity.com/paper/2111.04779/) (2021)
- [Monitoring and Adapting ML Models on Mobile Devices](https://mlsanity.com/paper/2305.07772/) (2023)
- [U-TOE: Universal TinyML On-board Evaluation Toolkit for Low-Power IoT](https://mlsanity.com/paper/2306.14574/) (2023)
- [A System for Real-Time Interactive Analysis of Deep Learning Training](https://mlsanity.com/paper/2001.01215/) (2020)

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

- [Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers](https://mlsanity.com/paper/2512.09800/) (2025)

## Abstract (arXiv)

TinyML models often operate in remote, dynamic environments without cloud connectivity, making them prone to failures. Ensuring reliability in such scenarios requires not only detecting model failures but also identifying their root causes. However, transient failures, privacy concerns, and the safety-critical nature of many applications-where systems cannot be interrupted for debugging-complicate the use of raw sensor data for offline analysis. We propose DEBUG-HD, a novel, resource-efficient on-device debugging approach optimized for KB-sized tinyML devices that utilizes hyper-dimensional computing (HDC). Our method introduces a new HDC encoding technique that leverages conventional neural networks, allowing DEBUG-HD to outperform prior binary HDC methods by 27% on average in detecting input corruptions across various image and audio datasets.