Colloquium: Abhinand Pusuluri (AWEP)

27 januari 2020 13:00 - Locatie: Lecture Room A, Faculty of Aerospace Engineering, Kluvyerweg 1, Delft

Noise-augmented offline training of ANN unresolved-scale models

An effective way to solve the forced Burgers equation in a variational multiscale framework is to close the system of equations using unresolved-scale interaction terms predicted by an artificial neural network. The goal of this thesis is to investigate the accuracy and stability of the said system by training a neural network offline with data enriched by two different noise addition techniques.