Dynamic Weight Alignment for Temporal Convolutional Neural Networks

TL;DR

This paper introduces a novel approach to enhance temporal CNNs by using dynamic programming and DTW for optimal weight-input alignment, improving robustness to temporal distortions across various datasets.

Contribution

It presents a new method employing Dynamic Time Warping for dynamic weight alignment in temporal CNNs, addressing limitations of fixed linear matching.

Findings

Improved accuracy on handwritten digit and character datasets

Enhanced robustness to temporal distortions in activity recognition

Demonstrated effectiveness across multiple real-world datasets

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.