Evolutionary machine learning of physics-based force fields in high-dimensional parameter-space
David van der Spoel, Julián Ramón Marrades Furquet, Kristian Kříž, A. Hosseini, Alfred Nordman, João Paulo, Marie‐Madeleine Walz, Paul J. van Maaren, Mohammad Mehdi Ghahremnapour
Abstract
This work presents the Alexandria Chemistry Toolkit (ACT), an open-source software for machine learning of physics-based force fields (FFs) from scratch, based on user-specified potential functions.
Topics & Concepts
Space (punctuation)PhysicsParameter spaceStatistical physicsTheoretical physicsArtificial intelligenceComputer scienceClassical mechanicsMathematicsGeometryOperating systemEvolutionary Algorithms and ApplicationsNeural Networks and ApplicationsReinforcement Learning in Robotics