PaperScope
LIVE · 2026-09-15 05:40 UTC

Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference

Niklas Summ, Xiao Wang, Hendrik Borras, Bernhard Klein, Holger Fröning

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.15527 v1
Category
Submitted
2026-09-14

Abstract

The energy efficiency of analog computing makes it one of the most promising candidates for deploying resource-intensive machine learning workloads on constrained platforms such as mobile and embedded devices. However, analog accelerators are inherently susceptible to noise and non-idealities arising from physical component variations, whose behavior is further sensitive to environmental factors. These effects can significantly degrade inference accuracy. In this work, we conduct a comprehensive experimental study on a representative example of analog hardware to investigate the impact of temperature. We first characterize the behavior of stochastic and systematic non-idealities across a range of operating temperatures. Following this, we compare a set of simulation-based and hardware-based mitigation strategies aimed at improving robustness against temperature-induced performance degradation. Our results suggest that temperature-induced degradation is driven primarily by systematic non-idealities rather than stochastic noise alone. Noise-aware training improves robustness, while hardware-in-the-loop training and temperature-aware calibration provide the strongest accuracy retention across varying thermal conditions.

Comment: Published at the ECML PKDD Conference 2026, at the 7th Workshop on IoT, Edge, and Mobile for Embedded Machine Learning

arXiv abs page · PDF · same-day batch