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

arXiv:2609.15527 · cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.LG

Submitted: 2026-09-14

Updated: 2026-09-14

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

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 32× in this paper · explained in 7 episodes
• Robustness — 20× in this paper · explained in 5 episodes
• Accuracy — 16× in this paper · explained in 1 episode
• Quantization — 7× in this paper · explained in 12 episodes
• Variance-Aware Noisy Training — 4× in this paper
• Quantization-Aware Training — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Energy Efficiency — 2× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes

Sources

• Uncertainty Reasoning with Photonic Bayesian Machines
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks