Active learning for regression of structure–property mapping: the importance of sampling and representation
Hao Liu, Berkay Yucel, Baskar Ganapathysubramanian, Surya R. Kalidindi, Daniel Wheeler, Olga Wodo
Abstract
We develop an active workflow for calibrating microstructure–property relationships when a large dataset of microstructures is available, but the cost associated with evaluating the properties associated is high.
Topics & Concepts
Property (philosophy)Representation (politics)Sampling (signal processing)RegressionComputer scienceArtificial intelligenceMathematicsStatisticsPolitical scienceComputer visionEpistemologyPoliticsPhilosophyLawFilter (signal processing)AI-based Problem Solving and PlanningBiomedical Text Mining and OntologiesFault Detection and Control Systems