mlsanityData to 14 Oct 2026

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

arXiv 2610.03402 ↗First posted 2 Oct 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

To deploy deep neural networks on edge hardware, highly efficient inference schemes are necessary that retain high accuracy. This work presents W16A16, a high precision (16-bit), fast speed, low energy quantization method. On a widely applied microcontroller architecture Armv7E-M, our proposed approach achieves faster speed and lower energy consumption on layer- and model-level compared to alternative quantization schemes. We analyze the architecture of Armv7E-M, explain the underlying principles behind the performance advantages of 16-bit approaches, and evaluate the empiric quantization errors for regression and classification tasks, as well as empiric time- and energy consumption in MCU deployment. We observe ca. 10 times lower quantization errors compared to 8-bit quantization schemes while achieving similar or better inference times and energy consumption.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 28 references that are in the map. First posted on arXiv 2 Oct 2026.

Builds on

14 of 28 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  4. 2021A White Paper on Neural Network Quantizationcited by 472
  5. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 434
  6. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 379
  7. 2023Atom: Low-bit Quantization for Efficient and Accurate LLM Servingcited by 272
  8. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  9. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  10. 2019Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollerscited by 33
  11. 2021Quantization and Deployment of Deep Neural Networks on Microcontrollerscited by 21
  12. 2021Differentiable Network Pruning for Microcontrollerscited by 16
2 more
  1. 2022Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compressioncited by 7
  2. 2025Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applicationscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks
  2. 2023Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge
  3. 2025Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference
  4. 2022AMED: Automatic Mixed-Precision Quantization for Edge Devices
  5. 2021VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference
  6. 2025MaRVIn: A Cross-Layer Mixed-Precision RISC-V Framework for DNN Inference, from ISA Extension to Hardware Acceleration
  7. 2024On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers
  8. 2023DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables