RNN GRU-D

Reported on 5 benchmarks across 5 tasks · 1 paper · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Time Series4 results

ImputationonMuJoCo
MSE (10^2, 50% missing)· 2016-06-06
0.748
best: 0.285 (Latent ODE (ODE enc))
SOTA
Recurrent Neural Networks for Multivariate Time Series with Missing Values arXiv:1606.01865
Time Series ForecastingonMuJoCo
MSE (10^-2, 50% missing)· 2016-06-06
5.833
best: 1.258 (Latent ODE (ODE enc))
SOTA
Recurrent Neural Networks for Multivariate Time Series with Missing Values arXiv:1606.01865
Time Series AnalysisonMuJoCo
MSE (10^-2, 50% missing)· 2016-06-06
5.833
best: 1.258 (Latent ODE (ODE enc))
SOTA
Recurrent Neural Networks for Multivariate Time Series with Missing Values arXiv:1606.01865
Multivariate Time Series ForecastingonMuJoCo
MSE (10^-2, 50% missing)· 2016-06-06
5.833
best: 1.258 (Latent ODE (ODE enc))
SOTA
Recurrent Neural Networks for Multivariate Time Series with Missing Values arXiv:1606.01865

Methodology1 result

Feature EngineeringonMuJoCo
MSE (10^2, 50% missing)· 2016-06-06
0.748
best: 0.285 (Latent ODE (ODE enc))
SOTA
Recurrent Neural Networks for Multivariate Time Series with Missing Values arXiv:1606.01865