Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means

Pengfei Xu; Yue Wang; Yang Zhao; Yingyan Lin

doi:10.1109/ISCAS.2019.8702185

Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means

Pengfei Xu, Yue Wang, Yang Zhao, Yingyan Lin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The record-breaking success of convolutional neural networks (CNNs) comes at the cost of a large amount of model parameters. The resulting prohibitive memory storage and data movement energy have been limiting the extensive deployment of deep learning on daily-life edge devices which usually have limited storage capability and are battery-powered. To this end, we explore the employment of a recently published weight clustering technique, called deep k-Means which makes use of the redundancy within CNN parameters for reduced memory storage and data movement, and demonstrate k-Means's effectiveness in the context of an interactive real-time object detection using three representative daily-life devices (iPhone, iPad and FPGA).

Original language	English (US)
Title of host publication	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728103976
DOIs	https://doi.org/10.1109/ISCAS.2019.8702185
State	Published - 2019
Externally published	Yes
Event	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Sapporo, Japan Duration: May 26 2019 → May 29 2019

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	2019-May
ISSN (Print)	0271-4310

Conference

Conference	2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019
Country/Territory	Japan
City	Sapporo
Period	5/26/19 → 5/29/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE

Publisher link

10.1109/ISCAS.2019.8702185

Find It

Find It at U of M Libraries

Cite this

Xu, P., Wang, Y., Zhao, Y., & Lin, Y. (2019). Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings Article 8702185 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.2019.8702185

Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means. / Xu, Pengfei; Wang, Yue; Zhao, Yang et al.
2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8702185 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Xu, P, Wang, Y, Zhao, Y & Lin, Y 2019, Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means. in 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings., 8702185, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019, Sapporo, Japan, 5/26/19. https://doi.org/10.1109/ISCAS.2019.8702185

Xu P, Wang Y, Zhao Y, Lin Y. Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means. In 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8702185. (Proceedings - IEEE International Symposium on Circuits and Systems). doi: 10.1109/ISCAS.2019.8702185

Xu, Pengfei ; Wang, Yue ; Zhao, Yang et al. / Live demonstration : Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means. 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - IEEE International Symposium on Circuits and Systems).

@inproceedings{118543c8d5f14cb2b1b939871f962b36,

title = "Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means",

abstract = "The record-breaking success of convolutional neural networks (CNNs) comes at the cost of a large amount of model parameters. The resulting prohibitive memory storage and data movement energy have been limiting the extensive deployment of deep learning on daily-life edge devices which usually have limited storage capability and are battery-powered. To this end, we explore the employment of a recently published weight clustering technique, called deep k-Means which makes use of the redundancy within CNN parameters for reduced memory storage and data movement, and demonstrate k-Means's effectiveness in the context of an interactive real-time object detection using three representative daily-life devices (iPhone, iPad and FPGA).",

author = "Pengfei Xu and Yue Wang and Yang Zhao and Yingyan Lin",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE; 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 ; Conference date: 26-05-2019 Through 29-05-2019",

year = "2019",

doi = "10.1109/ISCAS.2019.8702185",

language = "English (US)",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings",

}

TY - GEN

T1 - Live demonstration

T2 - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019

AU - Xu, Pengfei

AU - Wang, Yue

AU - Zhao, Yang

AU - Lin, Yingyan

PY - 2019

Y1 - 2019

N2 - The record-breaking success of convolutional neural networks (CNNs) comes at the cost of a large amount of model parameters. The resulting prohibitive memory storage and data movement energy have been limiting the extensive deployment of deep learning on daily-life edge devices which usually have limited storage capability and are battery-powered. To this end, we explore the employment of a recently published weight clustering technique, called deep k-Means which makes use of the redundancy within CNN parameters for reduced memory storage and data movement, and demonstrate k-Means's effectiveness in the context of an interactive real-time object detection using three representative daily-life devices (iPhone, iPad and FPGA).

AB - The record-breaking success of convolutional neural networks (CNNs) comes at the cost of a large amount of model parameters. The resulting prohibitive memory storage and data movement energy have been limiting the extensive deployment of deep learning on daily-life edge devices which usually have limited storage capability and are battery-powered. To this end, we explore the employment of a recently published weight clustering technique, called deep k-Means which makes use of the redundancy within CNN parameters for reduced memory storage and data movement, and demonstrate k-Means's effectiveness in the context of an interactive real-time object detection using three representative daily-life devices (iPhone, iPad and FPGA).

UR - http://www.scopus.com/inward/record.url?scp=85066801640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066801640&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.2019.8702185

DO - 10.1109/ISCAS.2019.8702185

M3 - Conference contribution

AN - SCOPUS:85066801640

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - 2019 IEEE International Symposium on Circuits and Systems, ISCAS 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 May 2019 through 29 May 2019

ER -

Live demonstration: Bringing powerful deep learning into daily-life devices (Mobiles and FPGAS) via deep k-means

Abstract

Publication series

Conference

Bibliographical note

Publisher link

Find It

Other files and links

Fingerprint

Cite this