Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.
Kappel, Anjula C
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Process-Informed Forecasting models incorporating deterministic production recipe priors outperform ARIMA and deep learning baselines in accuracy, physical plausibility, and noise resilience for temperature forecasting in pharmaceutical lyophilization.
citing papers explorer
-
Rethinking Random Transformers as Adaptive Sequence Smoothers for Sleep Staging
Randomly initialized Transformers act as adaptive sequence smoothers for sleep staging via a Random Attention Prior Kernel, with gains mainly from inductive bias rather than training.
-
Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing
Process-Informed Forecasting models incorporating deterministic production recipe priors outperform ARIMA and deep learning baselines in accuracy, physical plausibility, and noise resilience for temperature forecasting in pharmaceutical lyophilization.