Our new paper “Statistical Guarantees for Approximate Stationary Points of Simple Neural Networks” is now online. Well done, Mahsa and Fang! 🎉🎉

We have a new paper “VC-PCR: a prediction method based on supervised variable selection and clustering” about variable clustering in transcriptomics and in general. Great work especially from Rebecca, who just defended her PhD, and from Rainer and Bernadette, the two other members of our Belgian🇧🇪-American🇺🇸-German🇩🇪 tag team!

Our paper “Depth Normalization of Small RNA Sequencing: Using Data and Biology to Select a Suitable Method” is now available on arXiv. Great to work with you, Yannick and Li-Xuan! 🦠

We have submitted a new paper “copula-based normalizing flows.” Great to work with you, Mike and Asja! ☄️

We have analized the vanishing-gradient problem in deep learning and potential remedies here. Congratulations, Leni! 🏄

We two new papers on deep learning, one on targeted deep learning and one on robust deep learning. Well done, Shih-Ting!

We have composed an overview of activation functions in artificial neural networks here.

We analyze the optimization landscapes of feedforward neural networks here. We show especially that the landscapes of wide networks do not have spurious local minima.

We have discussed the role of statistics in artificial intelligence here.

We have established risk bounds for robust deep learning here.