← Back to all news
arXiv Machine Learning By Niklas Summ, Xiao Wang, Hendrik Borras, Bernhard Klein, Holger Fr\"oning

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

Read the original on arXiv Machine Learning →

The paper investigates how temperature affects analog deep neural network (DNN) inference, focusing on both stochastic and systematic non‑idealities in analog hardware. Experiments show that temperature‑induced performance loss is mainly driven by systematic errors rather than random noise. The study evaluates various mitigation techniques, finding that noise‑aware training and temperature‑aware calibration—especially hardware‑in‑the‑loop training—best preserve inference accuracy across different thermal conditions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 20

A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing

arXiv:2607. 16183v1 Announce Type: new Abstract: To address the escalating energy and latency demands of machine-learning workloads, we introduce a blueprint for an energy-efficient and fast thermodynamic computing stack that leverages stochastic analog processes in physical hardware.

By Owen Lockwood, J\'er\'emy B\'ejanin, Joost Bus, Christopher Chamberland, Patrick Huembeli, Frank Sch\"afer, Guillaume Verdon
More like this →
arXiv Machine Learning
Sep 7

Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware

The paper presents an empirically calibrated, state‑aware Dynamic Voltage and Frequency Scaling (DVFS) scheduler that eliminates thermal throttling on a passively cooled Raspberry Pi 5 during sustained YOLOv8n inference. By using time‑domain guards, absolute temperature bounds, and derivative triggers, the scheduler outperforms a temperature‑only baseline with a 6.8% higher frame rate and 1.9% less energy per frame, and it surpasses an actively cooled reference in energy efficiency. The study also identifies that the passive operating envelope closes at ambient temperatures above 27 °C, where nonlinear leakage undermines DVFS control, and demonstrates that correct scheduling can make mechanical cooling unnecessary within the mapped envelope.

By Aayush Marasini, Zhaoxian Zhou
efficiency
More like this →
arXiv Machine Learning
Sep 4

RACE-AIMC: Selective Inference for Heterogeneous Analog In-Memory Accelerators at the Edge

RACE-AIMC is a framework that selects a single analog in‑memory computing (AIMC) accelerator from a pool to meet a specified energy budget while providing a mathematically exact upper bound on its error rate. Offline, it evaluates each chip, chooses the best one, and computes the bound; online, only that chip runs and a lightweight check decides whether to accept its output or defer to a fallback. Simulations show the certified error stays below 10% (mean 7.83%) and the system achieves clean‑digital accuracy while reducing energy use by about 69% compared to running all chips.

By Osama Yousuf, Martin Lueker-Boden
More like this →
arXiv Machine Learning
Aug 27

Sample Margin-Aware Recalibration of Temperature Scaling

The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.

By Haolan Guo, Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu
benchmarkssafety
More like this →