S-PENNs inject epistemic uncertainty into hard-constrained GENERIC neural networks blockwise, preserving energy conservation and nonnegative entropy production in every sample, and use split conformal prediction to calibrate the intervals.
Structure-preserving deep learning.European journal of applied mathematics, 32(5):888– 936, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Structure-preserving uncertainty quantification for GENERIC dynamics
S-PENNs inject epistemic uncertainty into hard-constrained GENERIC neural networks blockwise, preserving energy conservation and nonnegative entropy production in every sample, and use split conformal prediction to calibrate the intervals.