Here we introduce a new model of natural textures based on the feature spaces of convolutional neural networks optimised for object recognition. Samples from the model are of high perceptual quality demonstrating the generative power of neural networks trained in a purely discriminative fashion. Within the model, textures are represented by the correlations between feature maps in several layers of the network. We show that across layers the texture representations increasingly capture the statistical properties of natural images while making object information more and more explicit. The model provides a new tool to generate stimuli for neuroscience and might offer insights into the deep representations learned by convolutional neural networks.

ELLIS (European Laboratory for Learning and Intelligent Systems) is a European initiative in AI with a focus on scientific excellence, innovation and societal impact. The initiative unites many of the leading machine learning researchers in Europe and aims to create a pan-European AI Lab. The ELLIS Institute Tübingen is sponsored with a 100 Mio EUR endowment from the Hector Foundation. We will be located near Stuttgart in the historic city of Tübingen, a beautiful university town in the southwest of Germany, tucked against a vast nature park. Major cities including Zurich, Munich and Frankfurt are within a few hours by public transportation.

The need for data privacy and security - enforced through increasingly strict data protection regulations - renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an'algorithm to the data' paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-source implementation of the PHT concept. Containerization allows us to easily deploy even complex data analysis pipelines (e.g, genomics, image analysis) across multiple sites in a secure and scalable manner. We discuss the underlying technological concepts, security models, and governance processes. The implementation has been successfully applied to distributed analyses of large-scale data, including applications of deep neural networks to medical image data. Keywords: Distributed Learning, Healthcare Machine Learning, Data Privacy, Biomedical Informatics, Healthcare Big Data.

ML Research Scientist at NT Parameter Lab Germany › Tübingen (Posted Oct 18 2022) Job description We are building a new group of ambitious, independent-minded researchers to tackle the trustworthiness of billion-scale ML models. The team will work on the in-house large language models and large-scale multi-modal models at Naver. As an independent researcher, you will be given the autonomy to define and solve problems in billion-scale models. You will present your results through academic publications and tech transfers. You will build unique expertise in dealing with billion-scale models.

We are building a new group of ambitious, independent-minded researchers to tackle the trustworthiness of billion-scale ML models. The team will work on the in-house large language models and large-scale multi-modal models at Naver. As an independent researcher, you will be given the autonomy to define and solve problems in billion-scale models. You will present your results through academic publications and tech transfers. You will build unique expertise in dealing with billion-scale models.

As the car with the blacked-out windows came to a halt in a sidestreet near Tübingen's botanical gardens, keen-eyed passersby may have noticed something unusual about its numberplate. In Germany, the first few letters usually denote the municipality where a vehicle is registered. The letter Y, however, is reserved for members of the armed forces. Military men are a rare, not to say unwelcome, sight in Tübingen. A picturesque 15th-century university town that brought forth great German minds including the philosopher Hegel and the poet Friedrich Hölderlin, it is also a modern stronghold of the German Green party, thanks to its left-leaning academic population. In 2018, there was growing resistance on campus against plans to establish Europe's leading artificial intelligence research hub in the surrounding area: the involvement of arms manufacturers in Tübingen's "cyber valley", argued students who occupied a lecture hall that year, brought shame to the university's intellectual tradition. Yet the two high-ranking officials in field-grey Bundeswehr uniforms who stepped out of the Y-plated vehicle on 1 February 2018 had travelled into hostile territory to shake hands on a collaboration with academia, the like of which the world had never seen before. The name of the initiative was Project Cassandra: for the next two years, university researchers would use their expertise to help the German defence ministry predict the future. Instead, the people the colonels had sought out in a stuffy top-floor room were a small team of literary scholars led by Jürgen Wertheimer, a professor of comparative literature with wild curls and a penchant for black roll-necks.

In the "Corona Summer" of 2020, Prof. Dr. Philipp Hennig remotely taught the course on Probabilistic Machine Learning within the Tübingen International Master Programme on Machine Learning. The course consists of two 90min lectures per week (26 lectures in total) plus a weekly practical / tutorial. Videos of all lectures are available on the youtube channel of the Tübingen Machine Learning Groups. The tutorials were taught by members of the Chair: Alexandra Gessner, Julia Grosse, Filip de Roos, Jonathan Wenger, Marius Hobbhahn, Nicholas Krämer, and Agustinus Kristiadi. The exercises and other material from these tutorials are available only to Tübingen students, via Ilias.

To participate in the discussions via chat you will have to register via Crowdcast for each conference day by clicking on the corresponding event on our Crowdcast profile - the participants' cameras and microphones will remain switched off. You need to enter your email address first and then your full name (first name and surname). If you only want to follow the talks, you can watch them via Youtube. Here you will find the live streams of all conference talks. Each talk takes 30 minutes plus 15 minutes discussion, each spotlight presentation 5 minutes plus 5 minutes discussion.

Motivated by the current COVID-19 outbreak, we introduce a novel epidemic model based on marked temporal point processes that is specifically designed to make fine-grained spatiotemporal predictions about the course of the disease in a population. Our model can make use and benefit from data gathered by a variety of contact tracing technologies and it can quantify the effects that different testing and tracing strategies, social distancing measures, and business restrictions may have on the course of the disease. Building on our model, we use Bayesian optimization to estimate the risk of exposure of each individual at the sites they visit, the percentage of symptomatic individuals, and the difference in transmission rate between asymptomatic and symptomatic individuals from historical longitudinal testing data. Experiments using real COVID-19 data and mobility patterns from T\"{u}bingen, a town in the southwest of Germany, demonstrate that our model can be used to quantify the effects of tracing, testing, and containment strategies at an unprecedented spatiotemporal resolution. To facilitate research and informed policy-making, particularly in the context of the current COVID-19 outbreak, we are releasing an open-source implementation of our framework at https://github.com/covid19-model.

Sebastian J. Schultheiss, Managing Director of Computomics, founded Computomics together with a very experienced board of scientific advisors from ETH Zurich, Max Planck Institute for Developmental Biology and the University of Tübingen. Sebastian studied Bioinformatics at University of Michigan and Tübingen. He worked on Machine Learning research and its application to biological data for his PhD degree at the Max Planck Institute for Developental Biology and FML. He brings startup experience, boinformatics skills and machine learning expertise to Computomics, which brings superior prediction accuracy and unprecedented integration of phenotyping, genotyping, management and environmental data to agriculture, enabling its clients to produce stable, value-added crops. He studied Bioinformatics at University of Tübingen and McGill, Montréal, and graduated with researching the evolution of epigenetic marks in plants at the Max Planck Institute for Developmental Biology, Tübingen.