Materials synthesizability and stability prediction using a semi-supervised teacher-student dual neural network
Daniel Gleaves, Nihang Fu, Edirisuriya M. Dilanga Siriwardane, Yong Zhao, Jianjun Hu
Abstract
A semi-supervised deep neural network (TSDNN) model based on teacher-student architecture is developed for high-performance formation energy and synthesizability prediction by exploiting a large number of unlabelled samples.
Topics & Concepts
Dual (grammatical number)Artificial neural networkStability (learning theory)Artificial intelligenceComputer scienceMachine learningPsychologyMathematics educationPhilosophyLinguisticsMachine Learning in Materials ScienceCatalysis and Oxidation ReactionsAdvanced Memory and Neural Computing