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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent few-shot learning works focus on training a model with priormeta-knowledge to fast adapt to new tasks with unseen classes and samples.However, conventional time-series classification algorithms fail to tackle thefew-shot scenario. Existing few-shot learning methods are proposed to tackleimage or text data, and most of them are neural-based models that lackinterpretability. This paper proposes an interpretable neural-based framework,namely \textit{Dual Prototypical Shapelet Networks (DPSN)} for few-shottime-series classification, which not only trains a neural network-based modelbut also interprets the model from dual granularity: 1) global overview usingrepresentative time series samples, and 2) local highlights usingdiscriminative shapelets. In particular, the generated dual prototypicalshapelets consist of representative samples that can mostly demonstrate theoverall shapes of all samples in the class and discriminative partial-lengthshapelets that can be used to distinguish different classes. We have derived 18few-shot TSC datasets from public benchmark datasets and evaluated the proposedmethod by comparing with baselines. The DPSN framework outperformsstate-of-the-art time-series classification methods, especially when trainingwith limited amounts of data. Several case studies have been given todemonstrate the interpret ability of our model.

Interpretable Time-series Classification on Few-shot Samples