Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Browse
New in RUL
About RUL
In numbers
Help
Sign in
Mobiprox : supporting dynamic approximate computing on mobiles
ID
Fabjančič, Matevž
(
Author
),
ID
Machidon, Octavian-Mihai
(
Author
),
ID
Sharif, Hashim
(
Author
),
ID
Zhao, Yifan
(
Author
),
ID
Misailović, Saša
(
Author
),
ID
Pejović, Veljko
(
Author
)
URL - Source URL, Visit
https://ieeexplore.ieee.org/document/10436434
PDF - Presentation file,
Download
(7,08 MB)
MD5: 566CB0A840B05AD13AAAA5861F478527
Image galllery
Abstract
Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input “difficulty”, or user needs. The existing compression techniques significantly reduce the memory, processing, and energy tax of DL, yet, the resulting models tend to be permanently impaired, sacrificing the inference power for reduced resource usage. The existing tunable compression approaches, on the other hand, require expensive re-training, do not support arbitrary strategies for adapting the compression and do not provide mobile-ready implementations. In this paper we present Mobiprox, a framework enabling mobile DL with flexible precision. Mobiprox implements tunable approximations of tensor operations and enables runtime-adaptable approximation of the individual network layers. A profiler and a tuner included with Mobiprox identify the most promising neural network approximation configurations leading to the desired inference quality with the minimal use of resources. Furthermore, we develop control strategies that depending on contextual factors, such as the input data difficulty, dynamically adjust the approximation levels across a mobile DL model’s layers. We implement Mobiprox in Android OS and through experiments in diverse mobile domains, including human activity recognition and spoken keyword detection, demonstrate that it can save up to 15% system-wide energy with a minimal impact on the inference accuracy.
Language:
English
Keywords:
approximate computing
,
context-awareness
,
mobile deep learning
,
ubiquitous computing
Work type:
Article
Typology:
1.01 - Original Scientific Article
Organization:
FRI - Faculty of Computer and Information Science
Publication status:
Published
Publication version:
Version of Record
Publication date:
01.01.2024
Year:
2024
Number of pages:
14 str.
Numbering:
Vol. , no.
PID:
20.500.12556/RUL-154705
UDC:
004
ISSN on article:
2327-4662
DOI:
10.1109/JIOT.2024.3365957
COBISS.SI-ID:
186557955
Publication date in RUL:
23.02.2024
Views:
266
Downloads:
14
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Share:
Record is a part of a journal
Title:
IEEE internet of things journal
Shortened title:
IEEE internet things j.
Publisher:
Institute of Electrical and Electronics Engineers
ISSN:
2327-4662
COBISS.SI-ID:
525375257
Licences
License:
CC BY 4.0, Creative Commons Attribution 4.0 International
Link:
http://creativecommons.org/licenses/by/4.0/
Description:
This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
Secondary language
Language:
Slovenian
Keywords:
približno računanje
,
kontekstno zavedanje
,
mobilno globoko učenje
,
vseprisotno računalništvo
Similar documents
Similar works from RUL:
Similar works from other Slovenian collections:
Back