English

Dynamic Weight Alignment for Temporal Convolutional Neural Networks

Computer Vision and Pattern Recognition 2019-02-08 v6 Machine Learning Neural and Evolutionary Computing

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.

Keywords

Cite

@article{arxiv.1712.06530,
  title  = {Dynamic Weight Alignment for Temporal Convolutional Neural Networks},
  author = {Brian Kenji Iwana and Seiichi Uchida},
  journal= {arXiv preprint arXiv:1712.06530},
  year   = {2019}
}

Comments

Accepted to ICASSP 2019

R2 v1 2026-06-22T23:21:54.683Z