signADAM and signADAM++ are new first-order optimizers that incorporate sign operations and a confidence-based sparsity mechanism, with claimed empirical superiority and theoretical convergence over ADAM and sign-based baselines.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Bayesian neural networks are used on EHR data to quantify prediction uncertainty from data noise, with experiments showing high-uncertainty cases degrade performance and can identify patients for data-quality intervention.
citing papers explorer
-
signADAM: Learning Confidences for Deep Neural Networks
signADAM and signADAM++ are new first-order optimizers that incorporate sign operations and a confidence-based sparsity mechanism, with claimed empirical superiority and theoretical convergence over ADAM and sign-based baselines.
-
Modeling the Uncertainty in Electronic Health Records: a Bayesian Deep Learning Approach
Bayesian neural networks are used on EHR data to quantify prediction uncertainty from data noise, with experiments showing high-uncertainty cases degrade performance and can identify patients for data-quality intervention.