Machine learning reaction barriers in low data regimes: a horizontal and diagonal transfer learning approach
Samuel G. Espley, Elliot H. E. Farrar, David Buttar, Simone Tomasi, Matthew N. Grayson
Abstract
Transfer learning (TL) is used to adapt existing neural networks to provide reaction barrier predictions for different reaction classes (horizontal TL) at higher levels of theory (diagonal TL) with tens of datapoints.
Topics & Concepts
DiagonalTransfer of learningArtificial neural networkTransfer (computing)Computer scienceArtificial intelligenceBiological systemPhysicsMathematicsGeometryParallel computingBiologyMachine Learning in Materials ScienceProtein Structure and DynamicsAdvanced Chemical Physics Studies