A factor-graph message-passing method for Bayesian neural networks that handles CNNs, avoids double-counting, and shows competitive accuracy with improved calibration on CIFAR-10.
Assumed density filtering methods for learning bayesian neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Approximate Message Passing for Bayesian Neural Networks
A factor-graph message-passing method for Bayesian neural networks that handles CNNs, avoids double-counting, and shows competitive accuracy with improved calibration on CIFAR-10.