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

Time-series classification approaches based on deep neural networks are easyto be overfitting on UCR datasets, which is caused by the few-shot problem ofthose datasets. Therefore, in order to alleviate the overfitting phenomenon forfurther improving the accuracy, we first propose Label Smoothing forInceptionTime (LSTime), which adopts the information of soft labels compared tojust hard labels. Next, instead of manually adjusting soft labels by LSTime,Knowledge Distillation for InceptionTime (KDTime) is proposed in order toautomatically generate soft labels by the teacher model. At last, in order torectify the incorrect predicted soft labels from the teacher model, KnowledgeDistillation with Calibration for InceptionTime (KDCTime) is proposed, where itcontains two optional calibrating strategies, i.e. KDC by Translating (KDCT)and KDC by Reordering (KDCR). The experimental results show that the accuracyof KDCTime is promising, while its inference time is two orders of magnitudefaster than ROCKET with an acceptable training time overhead.

KDCTime: Knowledge Distillation with Calibration on InceptionTime for Time-series Classification