Approximating functions, functionals, and operators using deep neural networks fordiverse applications
George Karniadakis is an applied mathematician, known for his wide-spectrum work on high-dimensional stochastic modeling and multiscale simulations of physical and biological systems. His current interest is physics-informed learning and neural networks, a field that he pioneered. He has also pioneered spectral/hp-element methods for fluids in complex geometries, general Polynomial Chaos for uncertainty quantification, and the theory of Sturm-Liouville theory for fractional partial differential equations. He is a Professor in Applied Mathematics at Brown University, Providence, USA, as well as research scientist at acific Northwest National Laboratory, Richland, USA. Since 2000, he has also been a visiting professor and senior lecturer of Ocean/Mechanical Engineering at Massachusetts Institute of Technology, Cambridge, USA. He has received the SIAM/ACM award in Computational Science and Engineering (2021) as well as the SIAM Ralph Kleiman Prize (2015) for the impact of his work on diverse applications for physical and biomedical problems.
Find the abstract here.