Deep Learning of Hierarchical Multiscale Differential Equation Time Steppers

This video by Yuying Liu introduces a new deep learning architecture to accurately and efficiently integrate multiscale differential equations forward in time. This approach is benchmarked on several illustrative dynamical systems. Check out the paper on arXiv: Hierarchical Deep Learning of Multiscale Differential Equation Time-Steppers Yuying Liu, J. Nathan Kutz, Steven L. Brunton