DEBUG-HD: Debugging TinyML models on-device using Hyper-Dimensional computing
This addresses reliability issues for TinyML applications in safety-critical, privacy-sensitive scenarios where cloud connectivity is unavailable.
The paper tackles the problem of debugging TinyML models in remote, dynamic environments by proposing DEBUG-HD, a resource-efficient on-device approach using hyper-dimensional computing, which outperforms prior methods by 27% on average in detecting input corruptions across image and audio datasets.
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.