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 prediction plays a crucial role in various industrial fields. Inrecent years, neural networks with a transformer backbone have achievedremarkable success in many domains, including computer vision and NLP. In timeseries analysis domain, some studies have suggested that even the simplest MLPnetworks outperform advanced transformer-based networks on time series forecasttasks. However, we believe these findings indicate there to be low-rankproperties in time series sequences. In this paper, we consider the low-passcharacteristics of transformers and try to incorporate the advantages of MLP.We adopt skip-layer connections inspired by Unet into traditional transformerbackbone, thus preserving high-frequency context from input to output, namelyU-shaped Transformer. We introduce patch merge and split operation to extractfeatures with different scales and use larger datasets to fully make use of thetransformer backbone. Our experiments demonstrate that the model performs at anadvanced level across multiple datasets with relatively low cost.

U-shaped Transformer: Retain High Frequency Context in Time Series Analysis