Dynamic Weight Alignment for Temporal Convolutional Neural Networks

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

3 被引用数 (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.

本文言語英語
ホスト出版物のタイトル2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版社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(印刷版)1520-6149

会議

会議44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
Country英国
CityBrighton
Period5/12/195/17/19

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

フィンガープリント 「Dynamic Weight Alignment for Temporal Convolutional Neural Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル