Itta Nozawa

A Monte Carlo Approach to Koopman Direct Encoding and Its Application to the Learning of Neural-Network Observables

This letter presents a computational method, called Bootstrapped Koopman Direct Encoding (B-KDE) that allows us to approximate the Koopman operator with high accuracy by combining Koopman Direct Encoding (KDE) with a deep neural network. Deep learning has been applied to the Koopman operator method