Partially Bayesian neural networks with only the first hidden and output layers probabilistic match fully Bayesian networks on active learning benchmarks while cutting compute by about four times.
Bayesian Conavigation: Dynamic Designing of the Material Digital Twins via Active Learning
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
cond-mat.dis-nn 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Active and transfer learning with partially Bayesian neural networks for materials and chemicals
Partially Bayesian neural networks with only the first hidden and output layers probabilistic match fully Bayesian networks on active learning benchmarks while cutting compute by about four times.