You are invited to attend our next UW CPAMI Graduate Seminar, which will include:
Dr. Siamak Mehrkanoonwill speak on "Teaching Machine to Learn The Solution of Dynamical Systems"
Abstract: : In the context of dynamical systems, the available differential equations together with initial/boundary conditions can be considered as side information. Here we use LS-SVM based core model to learn the solution of the dynamical system governed by differential algebraic equations (DAEs) as well as Partial Differential Equations (PDEs). The method utilizes few training points to learn a closed form approximate solution. Thanks to the optimization formulation, the method does not require index reduction techniques and can directly be applied to learn the state trajectories of the underlying system. The results of numerical experiments on different DEA systems with index from 0 to 3, as well as PDEs are presented and compared with analytic solutions to confirm the validity and applicability of the proposed method.
Short Biography: Dr. Siamak Mehrkanoon is currently a postdoctoral research fellow at CPAMI, University of Waterloo. He obtained his PhD degree in Machine Learning from KU Leuven, Belgium. His research interests include, but not limited to, Machine Learning, Deep Learning, Data Mining and Pattern Recognition.