Exercising is extremely important for our physical and mental health. Nowadays, it could not be more true, as we are facing numerous restrictions: We can’t go to the gym, we can’t meet our friends and family, we work from home and don’t have much time outdoor. Also, many of us live in tiny spaces. In this article, I am sharing a small set of exercises that are suitable for our confined lives. Maybe you’ll find them useful too!

Nowadays, it has become more and more common to publish on arXiv before peer-review. There are several (good) reasons for that: (1) Academic publishing takes too much time, and even then, (2) your paper often ends up behind a paywall. In over-hyped fields, the state of the art may change every month (or sometimes, week!), so it is a good way to “plant the flag” on your research idea. But what are the consequences of that?

I hate missing my train or arriving at the station to find out that my train is being delayed. This happens often, because German public transports are so unpredictable ! Since I take the train every day for work, it is also a pain to check online every time I leave. I found a solution to this problem, using a Raspberry Pi.

I was recently done reading “Kunst der Farbe” (Art of Color) by Johannes Itten. In this book, the great master of the Bauhaus exposes his theory about color and its role in artistic compositions. Itten makes the distinction between 7 kinds of contrast and shows the discrepancies between the objective physical properties of colors and our subjective perception. Itten introduces the 12-part color wheel to represent the visible spectrum of light.

Concept drift is a well-known issue in the data stream community. It means that the statistical properties of a data stream can change over time in unforeseen ways. In this article, I will talk about concept drift and its relation to the outlier detection problem. I will also introduce a prototype in R that can be used to simulate several kinds of drift.

I became recently interested in the Knight’s Tour problem. It is one of the oldest problem in computer science, known for more than 1000 years! I have written a program in Scala that solves it for arbitrary-shaped chessboards. I find the visual patterns in the solutions quite interesting. In this article, I will talk about that.

I came across the im2txt model for Tensorflow. It is a model developed by Google DeepMind that takes an image as input and creates a caption for it. I used the model to create captions for a few of my own images, and it was a lot of fun ! In this article, I will explain how to play with it. Then, I will show a few examples.

Outlier detection has the goal to reveal unusual patterns in data. Typical scenarios in predictive maintenance are the identification of failures, sensor malfunctions or intrusions. This is a challenging task, especially when the data is high-dimensional, because outliers become hidden and are visible only in particular subspaces. In this article, I will discuss approaches based on auto-encoder to discover outliers in high-dimensional data.

and welcome ! In this blog, I will speak about my work as a computer scientist, but also about art, culture and all the things I like. I am building this place to share freely a part of my views. Also, I want to get out of my comfort zone !