← Back to all news
arXiv Machine Learning By Rui Liu, Benjamin Paa{\ss}en

16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs

Read the original on arXiv Machine Learning →

The paper introduces W16A16, a 16‑bit precision quantization method for convolutional neural networks aimed at microcontroller units. On the Armv7E‑M architecture, W16A16 delivers faster inference speeds and lower energy consumption than existing quantization schemes while reducing quantization errors by roughly tenfold compared to 8‑bit approaches. The authors analyze the MCU architecture, explain why 16‑bit operations yield performance gains, and evaluate empirical errors and resource usage across regression and classification tasks.

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
Sep 24

RAMP: Robust Adaptive Mixed-Precision Quantization for Edge CPU Vision Models

The paper introduces RAMP, a method for robust adaptive mixed‑precision quantization of vision models on edge CPUs. It evaluates 13 sensitivity metrics across four neural networks, finding that Jensen‑Shannon Divergence consistently identifies layers that can be safely quantized. Using K‑Means clustering on these metrics, RAMP achieves near‑lossless accuracy with an average 1.81× speed‑up, while cautioning against excluding low‑speed‑up layers that can fragment the computational graph.

By David Poblaci\'on-Criado, Dario Garcia-Gasulla, Eduardo Quinones
efficiency
More like this →
arXiv Machine Learning
Sep 14

Efficient AI Model Deployment Using Quantization Analysis Tool

The paper introduces the Quantization Analysis Tool, a system built on the ONNX framework that streamlines quantization workflows for deep learning models. It offers layer‑wise sensitivity analysis, visualizations of weight and activation distributions, and guidance for selecting precision levels to balance model size, latency, and accuracy. Experiments on various neural network architectures show that the tool improves quantized accuracy and overall deployment efficiency.

By Dwith Chenna, Kanishka Macherla
efficiency
More like this →