Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression

Deutel M, Woller P, Mutschler C, Teich J (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Publisher: VDE

Series: MBMV

Book Volume: 26

Pages Range: 12

Conference Proceedings Title: MBMV 2023; 26th Workshop

Event location: Freiburg DE

ISBN: 978-3-8007-6065-7

URI: https://ieeexplore.ieee.org/document/10173060

Open Access Link: https://arxiv.org/abs/2205.10369

Abstract

Large Deep Neural Networks (DNNs) are the backbone of today's artificial intelligence due to their ability to make accurate predictions when trained on large data sets. With advancing technologies such as the Internet of Things, interpreting large amounts of data generated by sensors is becoming an increasingly important task. However, in many applications, not only the predictive performance but also the energy consumption of deep learning models is of great interest. This paper investigates the efficient deployment of deep learning models on resource-constrained microcontroller architectures via network compression. We present a methodology for systematically exploring different DNN pruning, quantization, and deployment strategies for different microcontroller architectures, with a focus on low-power ARM Cortex-M-based systems. The exploration allows to analyze trade-offs between key metrics such as accuracy, memory consumption, execution time, and power consumption. We discuss experimental results on three different DNN architectures and show that we can compress them to less than 10\% of their original parameter count before their prediction quality degrades. This also allows us to deploy and evaluate them on Cortex-M based microcontrollers.

Authors with CRIS profile

Mark Deutel Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design) Jürgen Teich Lehrstuhl für Informatik 12 (Hardware-Software-Co-Design)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Deutel, M., Woller, P., Mutschler, C., & Teich, J. (2023). Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression. In VDE (Eds.), MBMV 2023; 26th Workshop (pp. 12). Freiburg, DE: VDE.

MLA:

Deutel, Mark, et al. "Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compression." Proceedings of the Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen MBMV’23, Freiburg Ed. VDE, VDE, 2023. 12.

BibTeX: Download