Sparse Identification of Nonlinear Dynamics (SINDy)

This video illustrates a new algorithm for the sparse identification of nonlinear dynamics (SINDy). In this work, we combine machine learning, sparse regression, and dynamical systems to identify nonlinear differential equations purely from measurement data. From the Paper: Discovering governing equations from data by sparse identification of nonlinear dynamical systems. PNAS 113(15):3932—3937, 2016. Steven L. Brunton, Joshua L. Proctor, and J. Nathan Kutz Code available at: http://faculty.washington.edu/sbrunton/sparsedynamics.zip For more details, see our papers: https://scholar.google.com/citations?user=TjzWdigAAAAJ&hl=en http://www.pnas.org/content/113/15/3932 http://arxiv.org/abs/1509.03580 This video was produced at the University of Washington