English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we propose a method of improving temporal Convolutional NeuralNetworks (CNN) by determining the optimal alignment of weights and inputs usingdynamic programming. Conventional CNN convolutions linearly match the sharedweights to a window of the input. However, it is possible that there exists amore optimal alignment of weights. Thus, we propose the use of Dynamic TimeWarping (DTW) to dynamically align the weights to the input of theconvolutional layer. Specifically, the dynamic alignment overcomes issues suchas temporal distortion by finding the minimal distance matching of the weightsand the inputs under constraints. We demonstrate the effectiveness of theproposed architecture on the Unipen online handwritten digit and characterdatasets, the UCI Spoken Arabic Digit dataset, and the UCI Activities of DailyLife dataset.

Dynamic Weight Alignment for Temporal Convolutional Neural Networks