Sebastian Mitusch

S. Mitusch, S. W. Funke and M. Kuchta

Hybrid FEM-NN models: Combining artificial neural networks with the finite element method

Journal of Computational Physics

L. M. Valnes, S. Mitusch, G. Ringstad, P. K. Eide, S. W. Funke and K. Mardal

Apparent diffusion coefficient estimates based on 24 hours tracer movement support glymphatic transport in human cerebral cortex

Scientific Reports

J. S. Dokken, S. Mitusch and S. W. Funke

Automatic shape derivatives for transient PDEs in FEniCS and Firedrake

arxiv

S. Mitusch, S. W. Funke and M. Kuchta

Hybrid FEM-NN models: Combining artificial neural networks with the finite element method

Journal of Computational Physics

S. Mitusch, S. W. Funke and J. S. Dokken

dolfin-adjoint 2018.1: automated adjoints for FEniCS and Firedrake

Journal of Open Source Software

S. Mitusch and S. W. Funke

Algorithmic differentiation for coupled FEniCS and PyTorch models

S. W. Funke, J. S. Dokken and S. Mitusch

Algorithmic differentation for shape derivatives with PDE constraints

Berlin, Germany

J. S. Dokken

Algorithmic Differentiation for Shape Optimization Problems in the High Level Finite Element Framework FEniCS

SIAM Conference on Computational Science and Engineering (CSE19), Spokane, Washington, USA

S. Mitusch, S. W. Funke and J. S. Dokken

Recent developments in dolfin-adjoint

FEniCS'19, Washington DC, USA

S. W. Funke and S. Mitusch

Algorithmic differentiation for mixed FEniCS-Tensorflow models

Oxford, UK

S. Mitusch and S. W. Funke

A new algorithmic differentiation tool (not only) for FEniCS