Dynamic Weight Alignment for Temporal Convolutional Neural Networks

Brian Kenji Iwana, Seiichi Uchida

研究成果: 著書/レポートタイプへの貢献会議での発言

1 引用 (Scopus)

抄録

In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching of the weights and the inputs under constraints. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.

元の言語英語
ホスト出版物のタイトル2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版者Institute of Electrical and Electronics Engineers Inc.
ページ3827-3831
ページ数5
ISBN(電子版)9781479981311
DOI
出版物ステータス出版済み - 5 2019
イベント44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, 英国
継続期間: 5 12 20195 17 2019

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2019-May
ISSN(印刷物)1520-6149

会議

会議44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
英国
Brighton
期間5/12/195/17/19

Fingerprint

Neural networks
Convolution
Dynamic programming

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

これを引用

Iwana, B. K., & Uchida, S. (2019). Dynamic Weight Alignment for Temporal Convolutional Neural Networks. : 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 3827-3831). [8682908] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻数 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682908

Dynamic Weight Alignment for Temporal Convolutional Neural Networks. / Iwana, Brian Kenji; Uchida, Seiichi.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 3827-3831 8682908 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; 巻 2019-May).

研究成果: 著書/レポートタイプへの貢献会議での発言

Iwana, BK & Uchida, S 2019, Dynamic Weight Alignment for Temporal Convolutional Neural Networks. : 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682908, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 巻. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 3827-3831, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, 英国, 5/12/19. https://doi.org/10.1109/ICASSP.2019.8682908
Iwana BK, Uchida S. Dynamic Weight Alignment for Temporal Convolutional Neural Networks. : 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 3827-3831. 8682908. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682908
Iwana, Brian Kenji ; Uchida, Seiichi. / Dynamic Weight Alignment for Temporal Convolutional Neural Networks. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 3827-3831 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{d4019864b6e94d0387703b04145d3b14,
title = "Dynamic Weight Alignment for Temporal Convolutional Neural Networks",
abstract = "In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching of the weights and the inputs under constraints. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.",
author = "Iwana, {Brian Kenji} and Seiichi Uchida",
year = "2019",
month = "5",
doi = "10.1109/ICASSP.2019.8682908",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3827--3831",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Dynamic Weight Alignment for Temporal Convolutional Neural Networks

AU - Iwana, Brian Kenji

AU - Uchida, Seiichi

PY - 2019/5

Y1 - 2019/5

N2 - In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching of the weights and the inputs under constraints. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.

AB - In this paper, we propose a method of improving temporal Convolutional Neural Networks (CNN) by determining the optimal alignment of weights and inputs using dynamic programming. Conventional CNN convolutions linearly match the shared weights to a window of the input. However, it is possible that there exists a more optimal alignment of weights. Thus, we propose the use of Dynamic Time Warping (DTW) to dynamically align the weights to the input of the convolutional layer. Specifically, the dynamic alignment overcomes issues such as temporal distortion by finding the minimal distance matching of the weights and the inputs under constraints. We demonstrate the effectiveness of the proposed architecture on the Unipen online handwritten digit and character datasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of Daily Life dataset.

UR - http://www.scopus.com/inward/record.url?scp=85068971340&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068971340&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682908

DO - 10.1109/ICASSP.2019.8682908

M3 - Conference contribution

AN - SCOPUS:85068971340

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 3827

EP - 3831

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -