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

One of the latest self-supervised learning (SSL) methods, VICReg, showed agreat performance both in the linear evaluation and the fine-tuning evaluation.However, VICReg is proposed in computer vision and it learns by pullingrepresentations of random crops of an image while maintaining therepresentation space by the variance and covariance loss. However, VICReg wouldbe ineffective on non-stationary time series where different parts/crops ofinput should be differently encoded to consider the non-stationarity. Anotherrecent SSL proposal, Temporal Neighborhood Coding (TNC) is effective forencoding non-stationary time series. This study shows that a combination of aVICReg-style method and TNC is very effective for SSL on non-stationary timeseries, where a non-stationary seismic signal time series is used as anevaluation dataset.

VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Series