Koopman Operator, Geometry, and Learning of Dynamical Systems
Igor Mezić
Abstract
Koopman operator theory has recently emerged as one of the main candidates for machine learning of dynamical processes. In this article, we briefly describe its history and the current focus, setting it within the new concept of dynamic process representation.
Topics & Concepts
Operator (biology)GeometryDynamical systems theoryComputer scienceMathematicsPhysicsQuantum mechanicsBiochemistryTranscription factorRepressorChemistryGeneModel Reduction and Neural NetworksNeural Networks and Applications