AI Paper Atlas

Research map / Time series / Causal and generative time series

Fully Neural Network based Model for General Temporal Point Processes

Takahiro Omi, naonori ueda, Kazuyuki Aihara

NeurIPS 2019 · Time series › Causal and generative time series · approach: State-space and latent dynamics forecasting · 77 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
Use a flexible neural-network hazard model instead of fixed-form hazard modelsRNN temporal point process · Synthetic datasetsTest negative log-likelihoodImproved
Use a flexible neural-network hazard model instead of fixed-form hazard modelsRNN temporal point process · Real datasetsTest negative log-likelihood: greater than 0.5Improved
Use a flexible neural-network hazard model instead of the strongest baselineRNN temporal point process · Average across time-prediction datasetsMAE: 0.766 -> 0.756Improved
Use a flexible neural-network hazard model instead of the strongest baselineRNN temporal point process · N-PoissonMAE: 0.704 -> 0.710Hurt
Use a flexible neural-network hazard model instead of the strongest baselineRNN temporal point process · FinanceMAE: 0.839 -> 0.847Hurt
Use a flexible neural-network hazard model instead of the strongest baselineRNN temporal point process · SCMAE: 0.494 -> 0.496Hurt
Replace CT-LSTM with the proposed neural-network modelTemporal point process prediction · Average across datasetsMNLL difference vs CT-LSTM: 0.064Improved
Replace CT-LSTM with the proposed neural-network modelTemporal point process prediction · Average across datasetsMAE difference vs CT-LSTM: 0.009Improved

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