GTF-DEER augments the DEER framework with Generalized Teacher Forcing to allow effective parallel training of nonlinear recurrent models on extremely long sequences, improving dynamical systems reconstruction for data with long time scales.
MIT Press, 2016
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A new MoE training method integrates expert-level losses and partial online updates to improve forecasting accuracy and efficiency over standard statistical and neural models.
A pedestal-trained convolutional autoencoder identifies particle structures in CYGNO optical TPC images, retaining 93% of signal intensity while discarding 98% of the area at 25 ms per frame on a consumer GPU.
citing papers explorer
-
Parallel-in-Time Training of Recurrent Neural Networks for Dynamical Systems Reconstruction
GTF-DEER augments the DEER framework with Generalized Teacher Forcing to allow effective parallel training of nonlinear recurrent models on extremely long sequences, improving dynamical systems reconstruction for data with long time scales.
-
Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration
A new MoE training method integrates expert-level losses and partial online updates to improve forecasting accuracy and efficiency over standard statistical and neural models.
-
Fast reconstruction-based ROI triggering via anomaly detection in the CYGNO optical TPC
A pedestal-trained convolutional autoencoder identifies particle structures in CYGNO optical TPC images, retaining 93% of signal intensity while discarding 98% of the area at 25 ms per frame on a consumer GPU.