Here, you can find a list of all the talks I gave at conferences, webinars, podcasts, workshops, and all the other places you can and could hear me talk. You will also find a section with magazine articles and books I’ve written. :-)

If you have been enjoying my content and would like to help me be able to create more, please consider sending me a donation at . Thank you! :-)

Workshops I am giving

UPDATE: Before you take this course please consider the info about the sexual harassment scandal surrounding DataCamp!

For many machine learning problems, simply running a model out-of-the-box and getting a prediction is not enough; you want the best model with the most accurate prediction. One way to perfect your model is with hyperparameter tuning, which means optimizing the settings for that specific model. In this course, you will work with the caret, mlr and h2o packages to find the optimal combination of hyperparameters in an efficient manner using grid search, random search, adaptive resampling and automatic machine learning (AutoML). Furthermore, you will work with different datasets and tune different supervised learning models, such as random forests, gradient boosting machines, support vector machines, and even neural nets. Get ready to tune!

I offer a workshop on deep learning with Keras and TensorFlow using R. Date and place depend on who and how many people are interested, so please contact me either directly or via the workshop page: (the description is in German but I also offer to give the workshop in English).

Durch das stark wachsende Datenvolumen hat sich das Rollenverständnis von Data Scientists erweitert. Statt Machine-Learning-Modelle für einmalige Analysen zu erstellen, wird häufiger in konkreten Entwicklungsprojekten gearbeitet, in denen Prototypen in produktive Anwendungen überführt werden. Keras ist eine High-Level-Schnittstelle, die ein schnelles, einfaches und flexibles Prototypisieren von Neuronalen Netzwerken mit TensorFlow ermöglicht. Zusammen mit Luigi lassen sich beliebig komplexe Datenverarbeitungs-Workflows in Python erstellen. Das führt dazu, dass auch Nicht-Entwickler den End-2-End-Workflow des Keras-TensorFlow-Modells zur Produktionsreife leicht implementieren können.

Where you find my written word

Upcoming talks, webinars, podcasts, etc.

Past talks, webinars, podcasts, etc.

  • At this year’s data2day conference on October 20th 2020 I talked about The Good, the Bad and the Ugly: how (not) to visualize data. You can find the German slides here and the code to create all plots here.

Vortrag auf der M3 Online-Konferenz am 16.06.2020

Mit Machine Learning getroffene Entscheidungen sind inhärent schwierig – wenn nicht gar unmöglich – nachzuvollziehen. Ein scheinbar gutes Ergebnis mit Hilfe von maschinellen Lernverfahren ist oft schnell erzielt oder wird von anderen als bahnbrechend verkauft. Die Komplexität einiger der besten Modelle wie neuronaler Netze ist genau das, was sie so erfolgreich macht. Aber es macht sie gleichzeitig zu einer Black Box. Das kann problematisch sein, denn Geschäftsführer oder Vorstände werden weniger geneigt sein, einer Entscheidung zu vertrauen und nach ihr zu handeln, wenn sie sie nicht verstehen. Shapley Values, Local Interpretable Model-Agnostic Explanations (LIME) und Anchors sind Ansätze, diese komplexen Modelle zumindest teilweise nachvollziehbar zu machen. In diesem Vortrag erkläre ich, wie diese Ansätze funktionieren, und zeige Anwendungsbeispiele.

LERNZIELE * Die Teilnehmer erhalten Einblick in Möglichkeit, die komplexe Modelle erklärbar machen. * Sie lernen, Datensätze kritisch zu hinterfragen und angemessen aufzuteilen. * Und sie erfahren, unter welchen Bedingungen sie Entscheidungen durch Machine Learning vertrauen können.

  • On March, 15th, I talked about Deep Learning for Software Engineers at the AccsoCon 2019. You can find my slides here.

Deep Learning is one of the “hot” topics in the AI area – a lot of hype, a lot of inflated expectation, but also quite some impressive success stories. As some AI experts already predict that Deep Learning will become “Software 2.0”, it might be a good time to have a closer look at the topic. In this session I will try to give a comprehensive overview of Deep Learning. We will start with a bit of history and some theoretical foundations that we will use to create a little Deep Learning taxonomy. Then we will have a look at current and upcoming application areas: Where can we apply Deep Learning successfully and what does it differentiate from other approaches? Afterwards we will examine the ecosystem: Which tools and libraries are available? What are their strengths and weaknesses? And to complete the session, we will look into some practical code examples and the typical pitfalls of Deep Learning. After this session you will have a much better idea of the why, what and how of Deep Learning, including if and how you might want to apply it to your own work.

Traditional machine learning workflows focus heavily on model training and optimization; the best model is usually chosen via performance measures like accuracy or error and we tend to assume that a model is good enough for deployment if it passes certain thresholds of these performance criteria. Why a model makes the predictions it makes, however, is generally neglected. But being able to understand and interpret such models can be immensely important for improving model quality, increasing trust and transparency and for reducing bias. Because complex machine learning models are essentially black boxes and too complicated to understand, we need to use approximations to get a better sense of how they work. One such approach is LIME, which stands for Local Interpretable Model-agnostic Explanations and is a tool that helps understand and explain the decisions made by complex machine learning models. Dr. Shirin Glander is Data Scientist at codecentric AG. She has received a PhD in Bioinformatics and applies methods of analysis and visualization from different areas - for instance, machine learning, classical statistics, text mining, etc. -to extract and leverage information from data.

Introducing Deep Learning with Keras and Python Keras is a high-level API written in Python for building and prototyping neural networks. It can be used on top of TensorFlow, Theano or CNTK. In this talk we build, train and visualize a Model using Python and Keras - all interactive with Jupyter Notebooks!

In January 2018 I was interviewed for a tech podcast where I talked about machine learning, neural nets, why I love R and Rstudio and how I became a Data Scientist.

In December 2017 I talked about Explaining Predictions of Machine Learning Models with LIME at the Münster Data Science Meetup.

In September 2017 I gave a webinar for the Applied Epidemiology Didactic of the University of Wisconsin - Madison titled “From Biology to Industry. A Blogger’s Journey to Data Science.” I talked about how blogging about R and Data Science helped me become a Data Scientist. I also gave a short introduction to Machine Learning, Big Data and Neural Networks.

In March 2017 I gave a webinar for the ISDS R Group about my work on building machine-learning models to predict the course of different diseases. I went over building a model, evaluating its performance, and answering or addressing different disease related questions using machine learning. My talk covered the theory of machine learning as it is applied using R.


Shirin Glander, Fei He, Gregor Schmitz, Anika Witten, Arndt Telschow, J de Meaux; Genome Biology and Evolution, 22nd June 2018, evy124,

K Christin Falke · Shirin Glander · Fei He · Jinyong Hu · Juliette de Meaux · Gregor Schmitz., Nov. 2011, Current Opinion in Genetics & Development

Luisa Klotz et al. 2019. Science Translational Medicine, May 2019

Lena Wildschütz, Doreen Ackermann, Anika Witten, Maren Kasper, Martin Busch, Shirin Glander, Harutyun Melkony, Karoline Walscheid, Christoph Tappeiner, Solon Thanos, Andrei Barysenka, Jörg Koch, Carsten Heinz, Björn Laffer, Dirk Bauer, Monika Stoll, Simon König, Arnd Heiligenhaus. Journal of Autoimmunity, Volume 100, June 2019, Pages 75-83

Marie Liebmann, Stephanie Hucke, Kathrin Koch, Melanie Eschborn, Julia Ghelman, Achmet I. Chasan, Shirin Glander, Martin Schädlich, Meike Kuhlencord, Niklas M. Daber, Maria Eveslage, Marc Beyer, Michael Dietrich, Philipp Albrecht, Monika Stoll, Karin B. Busch, Heinz Wiendl, Johannes Roth, Tanja Kuhlmann, Luisa Klotz. Proceedings of the National Academy of Sciences, August 2018, DOI: 10.1073/pnas.1721049115

Ulas et al., May 2017, Nature Immunology