Next Article in Journal
Low-Overhead Reinforcement Learning-Based Power Management Using 2QoSM
Next Article in Special Issue
The Potential of SoC FPAAs for Emerging Ultra-Low-Power Machine Learning
Previous Article in Journal
A Standard-Cell-Based CMFB for Fully Synthesizable OTAs
Previous Article in Special Issue
A Generalistic Approach to Machine-Learning-Supported Task Migration on Real-Time Systems
 
 
Article

Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors

1
Electrical and Electronic Engineering, University of Bristol, Bristol BS8 1UB, UK
2
Sensata Systems, Interface House, Swindon SN4 8SY, UK
*
Author to whom correspondence should be addressed.
Academic Editor: Weidong Kuang
J. Low Power Electron. Appl. 2022, 12(2), 28; https://doi.org/10.3390/jlpea12020028
Received: 10 March 2022 / Revised: 12 April 2022 / Accepted: 12 May 2022 / Published: 18 May 2022
(This article belongs to the Special Issue Low Power AI)
This paper investigates the energy savings that near-subthreshold processors can obtain in edge AI applications and proposes strategies to improve them while maintaining the accuracy of the application. The selected processors deploy adaptive voltage scaling techniques in which the frequency and voltage levels of the processor core are determined at the run-time. In these systems, embedded RAM and flash memory size is typically limited to less than 1 megabyte to save power. This limited memory imposes restrictions on the complexity of the neural networks model that can be mapped to these devices and the required trade-offs between accuracy and battery life. To address these issues, we propose and evaluate alternative ‘big–little’ neural network strategies to improve battery life while maintaining prediction accuracy. The strategies are applied to a human activity recognition application selected as a demonstrator that shows that compared to the original network, the best configurations obtain an energy reduction measured at 80% while maintaining the original level of inference accuracy. View Full-Text
Keywords: near-subthreshold processor; energy efficient; edge computing; neural network; adaptive computing near-subthreshold processor; energy efficient; edge computing; neural network; adaptive computing
Show Figures

Figure 1

MDPI and ACS Style

Shen, Z.; Howard, N.; Nunez-Yanez, J. Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors. J. Low Power Electron. Appl. 2022, 12, 28. https://doi.org/10.3390/jlpea12020028

AMA Style

Shen Z, Howard N, Nunez-Yanez J. Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors. Journal of Low Power Electronics and Applications. 2022; 12(2):28. https://doi.org/10.3390/jlpea12020028

Chicago/Turabian Style

Shen, Zichao, Neil Howard, and Jose Nunez-Yanez. 2022. "Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors" Journal of Low Power Electronics and Applications 12, no. 2: 28. https://doi.org/10.3390/jlpea12020028

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop