4 year phd position on stochastic optimal control theory for neural networks
In the context of the Marie Curie NETT project
we have two 4 year PhD positions available in my research group in Nijmegen, the Netherlands.
The aim of the work package is to build neural architectures for stochastic optimal control and learning. The research is motivated by the recent work on path integral control methods. For this class of control methods, the optimal control can be computed using sampling.
This approach has shown to be very effective for robotics and learning. The current project will address the question of how such control computations can be implemented in neural networks.
The project requires advanced expertise on neural networks, control theory and machine learning. The candidates are not required to have good knowledge of these fields at the start of the project, but are expected to learn these topics.
Candidates should have a completed academic degree in theoretical physics, mathematics or engineering. As part of our commitment to promoting diversity, we particularly encourage female candidates to apply. To comply with the mobility rules of the Marie Curie Actions, applicants must not have resided, worked or studied in the Netherlands for more than 12 months in the three years prior to September 2012.