Please subscribe to our mailing list
to receive the latest information about seminars, conferences, grants, and resources!
Tuesday, February 2 at 2 p.m. via Zoom
Speaker: Professor Lin Lin, UC Berkely, Mathematics
Abstract: In recent years, deep learning has led to impressive results in many fields. I will introduce a multiscale artificial neural network for representing high-dimensional nonlinear maps based on the idea of hierarchical nested bases. This approach allows us to efficiently approximate discretized nonlinear maps arising from partial differential equations or integral equations. If time allows, will also discuss recent works on using neural networks to learn the mapping from the atomic positions to self-consistent electron densities obtained from density functional theory calculations.