AI Paper Atlas

Research map / Time series / Causal and generative time series

Sparse Gaussian Conditional Random Fields on Top of Recurrent Neural Networks

Xishun Wang, Minjie Zhang, Fenghui Ren

AAAI 2018 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add CoR (SGCRF on top of Bi-LSTM) to stacked Bi-LSTMsstacked Bi-LSTMs · large syntheticMAPE: 0.032 -> 0.026Improved
add CoR on top of Bi-LSTMsstacked Bi-LSTMs · large synthetictime usage: 5.43h -> 9.41hHurt
use stacked Bi-LSTMs instead of SGCRFSGCRF · large syntheticmemory usage: 17.21G -> 3.53GImproved
use stacked Bi-LSTMs instead of SGCRFSGCRF · large syntheticMAPE: 0.065 -> 0.032Improved
end-to-end training instead of alternative training (ablation)CoR(LSTM) · NPower Forecasting Challenge 2016 round 1MAPE: (4.11 ± 0.04)% -> (4.05 ± 0.05)%Improved
end-to-end training instead of alternative training (ablation)CoR(RNN) · NPower Forecasting Challenge 2016 round 1MAPE: (4.25 ± 0.04)% -> (4.19 ± 0.06)%Improved
end-to-end training instead of alternative training (ablation)CoR(LSTM) · NPower Forecasting Challenge 2016 round 2MAPE: (3.94 ± 0.03)% -> (3.87 ± 0.03)%Improved
feature engineering for SGCRFSGCRF · NPower Forecasting Challenge 2016 round 1MAPE: 5.83% -> 4.91%Improved
add CoR to stacked Bi-RNNsstacked Bi-RNNs · NPower Forecasting Challenge 2016 round 1MAPE: (4.88 ± 0.21)% -> (4.19 ± 0.06)%Improved
add CoR to stacked Bi-LSTMsstacked Bi-LSTMs · NPower Forecasting Challenge 2016 round 2MAPE: (4.31 ± 0.14)% -> (3.87 ± 0.03)%Improved
replace stacked Bi-RNNs with stacked Bi-LSTMsstacked Bi-RNNs · NPower Forecasting Challenge 2016 round 1MAPE: (4.88 ± 0.21)% -> (4.43 ± 0.16)%Improved
add feature engineering to gradient boostingGradient boosting · NPower Forecasting Challenge 2016MAPE: 4.90%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy