Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2020.04.103
Abstract: Abstract Deep Neural Networks (DNNs) have achieved state-of-the-art accuracy performance in many tasks. However, recent works have pointed out that the outputs provided by these models are not well-calibrated, seriously limiting their use in critical… read more here.
Keywords: calibration; neural networks; bayesian neural; calibration deep ... See more keywords