In magnetic particle imaging (MPI), the spatial distribution of magnetic nanoparticles is determined by applying various static and dynamic magnetic fields. Due to the complex physical behavior of the nanoparticles, it is challenging to determine the MPI system matrix in practice. Since the first publication on MPI in 2005, different methods that rely on measurements or simulations for the determination of the MPI system matrix have been proposed. Some methods restrict the simulation to an idealized model to speed up data reconstruction by exploiting the structure of an idealized MPI system matrix. Recently, a method that processes the measurement data in x-space rather than frequency space has been proposed. In this work, we compare the different approaches for image reconstruction in MPI and show that the x-space and the frequency space reconstruction techniques are equivalent.

By recovering the full particle signal the SNR can be improved and errors in the x-space reconstruction are prevented. The authors show that the combined method provides this full particle signal and makes it possible to improve image quality.

No abstract

No abstract

Abstract. Developing superior artificial board-game players is a widelystudied area of Artificial Intelligence. Among the most challenging games is the Asian game of Go, which, despite its deceivingly simple rules, has eluded the development of artificial expert players. In this paper we attempt to tackle this challenge through a combination of two recent developments in Machine Learning. We employ Multi-Dimensional Recurrent Neural Networks with Long Short-Term Memory cells to handle the multi-dimensional data of the board game in a very natural way. In order to improve the convergence rate, as well as the ultimate performance, we train those networks using Policy Gradients with Parameter-based Exploration, a recently developed Reinforcement Learning algorithm which has been found to have numerous advantages over Evolution Strategies. Our empirical results confirm the promise of this approach, and we discuss how it can be scaled up to expert-level Go players.