Neural networks for N-body simulations.
In this project, we will solve
the gravitational few-body problem using neural networks. This
approach is possible because the underlying equations of motion are
chaotic. Consequently, solutions obtained using traditional methods on
computers only provide a statistical answer, which can as well be
obtained by a neural network. We will train deep artificial
neural-networks on ensembles of converged solutions to the few-body
problem. The trained network will subsequently be replacing the
expensive few-body calculations in large simulations of dense star
clusters. This should lead to considerable speed-up compared to more
traditional direct integration.
This project is part of a larger project in collaboration with
researchers of the Eindhoven University of Technology (Department of
Mathematics and Computer Science and the Department of Physics), and
the Center for Mathematics and Computer Science (CWI) in Amsterdam.
In total 6 PhD students will be hired to work as a team on one of the
1) Algorithms for the discovery of interpretable latent variables.
2) Mimetic, hierarchical training algorithms for neural networks.
3) Dynamic neural networks and their relation to state-space methods.
4) Machine learning using constrained neural networks and differential equations.
5) Machine learning for analysis and control of complex fluid flows.6) Neural networks for N-body simulations (this project)
for details, see: https://local.strw.leidenuniv.nl/jobs/unravel.php
Please apply via this link: https://jobs.strw.leidenuniv.nl/2020/unravel/
© 2019 American Astronomical Society