An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection

Takuya Sakuma; Hiroki Matsutani

doi:10.1109/COOLCHIPS49199.2020.9097631

An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection

Takuya Sakuma, Hiroki Matsutani

Department of Information and Computer Science

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

3 Citations (Scopus)

Abstract

Toward on-device anomaly detection for time-series data, in this paper, we analyze Echo State Network (ESN), which is a simple form of Recurrent Neural Networks (RNNs), and propose its area-efficient implementation. It is evaluated in terms of the anomaly detection capability and area. (Keywords: On-device learning, Machine learning, and Anomaly detection)

Original language	English
Title of host publication	IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728163475
DOIs	https://doi.org/10.1109/COOLCHIPS49199.2020.9097631
Publication status	Published - 2020 Apr
Event	23rd IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Kokubunji, Japan Duration: 2020 Apr 15 → 2020 Apr 17

Publication series

Name	IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings

Conference

Conference	23rd IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020
Country/Territory	Japan
City	Kokubunji
Period	20/4/15 → 20/4/17

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Hardware and Architecture
Software
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality

Access to Document

10.1109/COOLCHIPS49199.2020.9097631

Cite this

Sakuma, T., & Matsutani, H. (2020). An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection. In IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings Article 9097631 (IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COOLCHIPS49199.2020.9097631

An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection. / Sakuma, Takuya; Matsutani, Hiroki.
IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9097631 (IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings).

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

Sakuma, T & Matsutani, H 2020, An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection. in IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings., 9097631, IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 23rd IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020, Kokubunji, Japan, 20/4/15. https://doi.org/10.1109/COOLCHIPS49199.2020.9097631

Sakuma T, Matsutani H. An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection. In IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9097631. (IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings). doi: 10.1109/COOLCHIPS49199.2020.9097631

Sakuma, Takuya ; Matsutani, Hiroki. / An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection. IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings).

@inproceedings{935a7b4691b34d8e8598c5798693d82f,

title = "An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection",

abstract = "Toward on-device anomaly detection for time-series data, in this paper, we analyze Echo State Network (ESN), which is a simple form of Recurrent Neural Networks (RNNs), and propose its area-efficient implementation. It is evaluated in terms of the anomaly detection capability and area. (Keywords: On-device learning, Machine learning, and Anomaly detection)",

author = "Takuya Sakuma and Hiroki Matsutani",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 23rd IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 ; Conference date: 15-04-2020 Through 17-04-2020",

year = "2020",

month = apr,

doi = "10.1109/COOLCHIPS49199.2020.9097631",

language = "English",

series = "IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings",

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

booktitle = "IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings",

}

TY - GEN

T1 - An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection

AU - Sakuma, Takuya

AU - Matsutani, Hiroki

PY - 2020/4

Y1 - 2020/4

N2 - Toward on-device anomaly detection for time-series data, in this paper, we analyze Echo State Network (ESN), which is a simple form of Recurrent Neural Networks (RNNs), and propose its area-efficient implementation. It is evaluated in terms of the anomaly detection capability and area. (Keywords: On-device learning, Machine learning, and Anomaly detection)

AB - Toward on-device anomaly detection for time-series data, in this paper, we analyze Echo State Network (ESN), which is a simple form of Recurrent Neural Networks (RNNs), and propose its area-efficient implementation. It is evaluated in terms of the anomaly detection capability and area. (Keywords: On-device learning, Machine learning, and Anomaly detection)

UR - http://www.scopus.com/inward/record.url?scp=85086037296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086037296&partnerID=8YFLogxK

U2 - 10.1109/COOLCHIPS49199.2020.9097631

DO - 10.1109/COOLCHIPS49199.2020.9097631

M3 - Conference contribution

AN - SCOPUS:85086037296

T3 - IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings

BT - IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 23rd IEEE Symposium on Low-Power and High-Speed Chips and Systems, COOL CHIPS 2020

Y2 - 15 April 2020 through 17 April 2020

ER -

An Area-Efficient Implementation of Recurrent Neural Network Core for Unsupervised Anomaly Detection

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this