الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Liu, R., & Paaßen, B. (2026). 16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs. https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs
MLA 9
Liu, Rui, and Benjamin Paaßen. "16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs." https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs.
شيكاغو (المؤلف–التاريخ)
Liu, Rui, and Benjamin Paaßen. 2026. "16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs." https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs.
هارفارد
Liu, R. and Paaßen, B. (2026) '16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs', Available at: https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs.
فانكوفر
Liu R, Paaßen B. 16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs. https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs
IEEE
R. Liu, and B. Paaßen, "16-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit Costs," https://omanscience.com/ar/articles/16-bit-precision-of-convolutional-neural-networks-on-microcontroller-units-for-8-bit-costs.