Back to Search Start Over

Power-Efficient Implementation of Ternary Neural Networks in Edge Devices

Authors :
Molina Fernández, Miguel
Mendez Gomez, Javier
Morales, Diego
Castillo, Encarnación
López Vallejo, Marisa
Pegalajar, Manuel
Molina Fernández, Miguel
Mendez Gomez, Javier
Morales, Diego
Castillo, Encarnación
López Vallejo, Marisa
Pegalajar, Manuel
Source :
IEEE Internet of Things Journal, ISSN 2327-4662, 2022-10, Vol. 9, No. 20
Publication Year :
2022

Abstract

There is a growing interest in pushing computation to the edge, especially the problem-solving abilities of artificial neural networks (ANNs). This article presents a simplified method to obtain a ternary neural network based on the multilayer perceptron. The method is focused on resource-constrained devices, where memory, computing power, and battery are some of the most relevant constraints. A dynamic threshold is estimated to perform ternarization, and a new pruning technique is proposed to obtain a drastic reduction in the ANN’s size, with the corresponding decrease in resource utilization and power consumption of the resulting hardware. In addition, a support framework has been developed to automate hardware design exploration and generation from the network trained in software. Experimental results show that the proposed method and architecture, when implemented in a field-programmable gate array (FPGA), provide excellent figures in power (0.11–0.13 W) and efficiency (1225–1448 kfps/W) with respect to state of the art, being its efficiency double than the maximum one reported previously.

Details

Database :
OAIster
Journal :
IEEE Internet of Things Journal, ISSN 2327-4662, 2022-10, Vol. 9, No. 20
Notes :
application/pdf, English
Publication Type :
Electronic Resource
Accession number :
edsoai.on1432957469
Document Type :
Electronic Resource