18377526. ACTIVE LEARNING MACHINE LEARNING INTERATOMIC POTENTIAL (MLIP) TRAINING METHODS (Robert Bosch GmbH)
ACTIVE LEARNING MACHINE LEARNING INTERATOMIC POTENTIAL (MLIP) TRAINING METHODS
Organization Name
Inventor(s)
Shao-Chun Lee of Champaign IL US
Mordechai Kornbluth of Brighton MA US
Nicola Molinari of Cambridge MA US
Daniil Kitchaev of Brookline MA US
ACTIVE LEARNING MACHINE LEARNING INTERATOMIC POTENTIAL (MLIP) TRAINING METHODS
This abstract first appeared for US patent application 18377526 titled 'ACTIVE LEARNING MACHINE LEARNING INTERATOMIC POTENTIAL (MLIP) TRAINING METHODS
Original Abstract Submitted
An active learning machine learning interatomic potential (MLIP) training method. The method includes receiving one or more datasets associated with a material. The method further includes actively learning a dynamic trajectory in response to the one or more datasets associated with the material. The dynamic trajectory samples a first set of structures and progresses to a second set of structures to create an actively learned MLIP to predict one or more atomic values of the material. The MLIP training method may include biasing the sampling with, for instance, temperature and/or potential biasing.