Two-stage transfer learning from approximate AGL thermal-conductivity data improves deep-learning predictions on diverse small DFT datasets but harms a specialized half-Heusler dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Transfer Learning for Deep Learning-based Prediction of Lattice Thermal Conductivity
Two-stage transfer learning from approximate AGL thermal-conductivity data improves deep-learning predictions on diverse small DFT datasets but harms a specialized half-Heusler dataset.