Active learning with SNGP and BNN-NCP models constructs QuaLiKiz surrogate training sets from 100 to 10,000 points, beating random sampling and approaching prior ensemble-based ADEPT efficiency.
Latent derivative bayesian last layer networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.plasm-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models
Active learning with SNGP and BNN-NCP models constructs QuaLiKiz surrogate training sets from 100 to 10,000 points, beating random sampling and approaching prior ensemble-based ADEPT efficiency.