Povzetek

Edge intelligence is currently facing several important challenges hindering its performance, with the major drawback being meeting the high resource requirements of deep learning by the resource-constrained edge computing devices. The most recent adaptive neural network compression techniques demonstrated, in theory, the potential to facilitate the flexible deployment of deep learning models in real-world applications. However, their actual suitability and performance in ubiquitous or edge computing applications has not, to this date, been evaluated. In this context, our work aims to bridge the gap between the theoretical resource savings promised by such approaches and the requirements of a real-world mobile application by introducing algorithms that dynamically guide the compression rate of a neural network according to the continuously changing context in which the mobile computation is taking place. Through an in-depth trace-based investigation, we confirm the feasibility of our adaptation algorithms in offering a scalable trade-off between the inference accuracy and resource usage. We then implement our approach on real-world edge devices and, through a human activity recognition application, confirm that it offers efficient neural network compression adaptation in highly dynamic environments. The results of our experiment with 21 participants show that, compared to using static network compression, our approach uses 2.18× less energy with only a 1.5% drop in the average accuracy of the classification.

Ključne besede

mobilno zaznavanje;nevronske mreže;dinamična optimizacija;kvantizacija;tanjšanje globokih mrež;mobile sensing;neural networks;dynamic optimization;quantization;DNN slimming;

Podatki

Jezik: Angleški jezik
Leto izida:
Tipologija: 1.01 - Izvirni znanstveni članek
Organizacija: UL FRI - Fakulteta za računalništvo in informatiko
UDK: 004
COBISS: 89465859 Povezava se bo odprla v novem oknu
ISSN: 2079-9292
Št. ogledov: 239
Št. prenosov: 59
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Sekundarni jezik: Slovenski jezik
Sekundarne ključne besede: mobilno zaznavanje;nevronske mreže;dinamična optimizacija;kvantizacija;tanjšanje globokih mrež;
Vrsta dela (COBISS): Članek v reviji
Strani: str. 1-23
Letnik: ǂVol. ǂ10
Zvezek: ǂiss. ǂ23
Čas izdaje: Dec. 2021
DOI: 10.3390/electronics10232958
ID: 15327521