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/

Zendy Plus

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

Zendy Tools

Zendy Open

Ordinary Differential Equations (ODE) based models have become popular asfoundation models for solving many time series problems. Combining neural ODEswith traditional RNN models has provided the best representation for irregulartime series. However, ODE-based models typically require the trajectory ofhidden states to be defined based on either the initial observed value or themost recent observation, raising questions about their effectiveness whendealing with longer sequences and extended time intervals. In this article, weexplore the behaviour of the ODE models in the context of time series data withvarying degrees of sparsity. We introduce SeqLink, an innovative neuralarchitecture designed to enhance the robustness of sequence representation.Unlike traditional approaches that solely rely on the hidden state generatedfrom the last observed value, SeqLink leverages ODE latent representationsderived from multiple data samples, enabling it to generate robust datarepresentations regardless of sequence length or data sparsity level. The coreconcept behind our model is the definition of hidden states for the unobservedvalues based on the relationships between samples (links between sequences).Through extensive experiments on partially observed synthetic and real-worlddatasets, we demonstrate that SeqLink improves the modelling of intermittenttime series, consistently outperforming state-of-the-art approaches.

SeqLink: A Robust Neural-ODE Architecture for Modelling Partially Observed Time Series