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

The marriage of recurrent neural networks and neural ordinary differentialnetworks (ODE-RNN) is effective in modeling irregularly-observed sequences.While ODE produces the smooth hidden states between observation intervals, theRNN will trigger a hidden state jump when a new observation arrives, thus causethe interpolation discontinuity problem. To address this issue, we propose thecubic spline smoothing compensation, which is a stand-alone module upon eitherthe output or the hidden state of ODE-RNN and can be trained end-to-end. Wederive its analytical solution and provide its theoretical interpolation errorbound. Extensive experiments indicate its merits over both ODE-RNN and cubicspline interpolation.

Cubic Spline Smoothing Compensation for Irregularly Sampled Sequences