A decoupled Bayesian neural network that maps a DNN's logits to calibrated probabilities consistently reduces expected calibration error, at the cost of some accuracy loss on complex datasets.
Vaswani, et al., Attention is all you need, in: I
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
A decoupled Bayesian neural network that maps a DNN's logits to calibrated probabilities consistently reduces expected calibration error, at the cost of some accuracy loss on complex datasets.