University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Deep neural network algorithms for oscillatory flows and operators, and high dimensional Fokker-Planck equations

Deep neural network algorithms for oscillatory flows and operators, and high dimensional Fokker-Planck equations

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact nobody.

MDLW03 - Deep learning and partial differential equations

In this talk, we will present results on new types of deep neural network (DNN) in the following areas: (a) a multi-scale DNN method for solving  highly oscillatory Navier-Stokes flows in complex domains (b) a multiscale DNN learning algorithm for nonlinear operators in highly oscillatory function spaces encountered in  seismic wave responses and forward and inverse problems of high frequency wave scattering; (c) a DNN based on forward and backward stochastic differential equations (FBSDEs) for high dimensional PDEs such as Fokker-Planck equations in statistical description of biochemical systems, with application to compute the committor functions and reaction rates in transition path sampling theory of complex chemical and biological systems.

This talk is part of the Isaac Newton Institute Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity