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 data is ubiquitous in research as well as in a wide variety ofindustrial applications. Effectively analyzing the available historical dataand providing insights into the far future allows us to make effectivedecisions. Recent research has witnessed the superior performance oftransformer-based architectures, especially in the regime of far horizon timeseries forecasting. However, the current state of the art sparse Transformerarchitectures fail to couple down- and upsampling procedures to produce outputsin a similar resolution as the input. We propose the Yformer model, based on anovel Y-shaped encoder-decoder architecture that (1) uses direct connectionfrom the downscaled encoder layer to the corresponding upsampled decoder layerin a U-Net inspired architecture, (2) Combines the downscaling/upsampling withsparse attention to capture long-range effects, and (3) stabilizes theencoder-decoder stacks with the addition of an auxiliary reconstruction loss.Extensive experiments have been conducted with relevant baselines on fourbenchmark datasets, demonstrating an average improvement of 19.82, 18.41percentage MSE and 13.62, 11.85 percentage MAE in comparison to the currentstate of the art for the univariate and the multivariate settings respectively.

Yformer: U-Net Inspired Transformer Architecture for Far Horizon Time Series Forecasting