M. Michael Denner

Jens Oppliger, M. Michael Denner, Julia Küspert et al.

Removal or cancellation of noise has wide-spread applications for imaging and acoustics. In every-day-life applications, denoising may even include generative aspects, which are unfaithful to the ground truth. For scientific use, however, denoising must reproduce the ground truth accurately. Here, we show how data can be denoised via a deep convolutional neural network such that weak signals appear with quantitative accuracy. In particular, we study X-ray diffraction on crystalline materials. We demonstrate that weak signals stemming from charge ordering, insignificant in the noisy data, become visible and accurate in the denoised data. This success is enabled by supervised training of a deep neural network with pairs of measured low- and high-noise data. We demonstrate that using artificial noise does not yield such quantitatively accurate results. Our approach thus illustrates a practical strategy for noise filtering that can be applied to challenging acquisition problems.

Titus Neupert, Mark H Fischer, Eliska Greplova et al.

This is an introductory machine-learning course specifically developed with STEM students in mind. Our goal is to provide the interested reader with the basics to employ machine learning in their own projects and to familiarize themself with the terminology as a foundation for further reading of the relevant literature. In these lecture notes, we discuss supervised, unsupervised, and reinforcement learning. The notes start with an exposition of machine learning methods without neural networks, such as principle component analysis, t-SNE, clustering, as well as linear regression and linear classifiers. We continue with an introduction to both basic and advanced neural-network structures such as dense feed-forward and conventional neural networks, recurrent neural networks, restricted Boltzmann machines, (variational) autoencoders, generative adversarial networks. Questions of interpretability are discussed for latent-space representations and using the examples of dreaming and adversarial attacks. The final section is dedicated to reinforcement learning, where we introduce basic notions of value functions and policy learning.