The participation to the Summer School is free of charge.
For late registrations, please contact the organizing committee at datascienceschool@uni.lu.
The program of the Summer School will be made of the following workshops and activities.
Data visualization is the representation of data through use of common graphics, such as charts, plots, infographics, and even animations. In modern societies, a vast amount of data is produced, collected and analysed at all times and everywhere. The mountains of data that accumulate every day need to be sifted through, processed and evaluated. For people, however, it can be difficult to extract clear statements from raw data. Visualising data helps bring order and meaning to the chaos of numbers. Data visualisation turns abstract numbers into stories; it produces insight and knowledge. During the morning session we will dive into the world of data visualization. In the afternoon we will then produce a new data visualisation and tell our own story.
Craters are distinctive features on the surfaces of most terrestrial planets such as Mars and Venus. The distribution of craters reveals the relative ages of surface units and provides information on surface geology. Extracting craters is one of the fundamental tasks in planetary research. Although many automated crater detection algorithms have been developed to extract craters from image or topographic data, most of them are applicable only in particular regions, and only a few can be widely used, especially in complex surface settings. On the other side, once we have a reasonable craters data, statistics play an important role in better understanding their features, in particular their distribution.
In this workshop, we will demonstrate to participants how basic methodologies with directional statistics and machine learning/deep learning models help in the detection and analysis of craters in our Universe.
A pizza chain runs stores in various college and university campuses, and the manager hypothesizes that the quarterly sales revenue of each store (y) is dependent on the total number of registered students on the campus (x). The workshop aims to investigate the relationship between x and y through regression analysis, specifically by using a simple regression model. By analyzing data, participants will learn fundamental techniques for crafting regression equations and methods for evaluating the quality of their estimation.
A set of randomly generated real numbers is said to follow Benford’s law if the first leading (non-zero) digit of each random number follows a given distribution. This probability distribution doesn’t coincide with the uniform distribution over the set {1, 2, 3, 4, 5, 6, 7, 8, 9}. Oddly enough, a lot of real-world datasets observed in various unrelated fields seem to follow Benford’s law. This phenomenon is quite intriguing since, for most of these real world ex- amples it is natural to assume that the numbers are uniformly distributed over some interval so that most people would think that their first leading digit must also be uniformly distributed. We investigate this apparent paradox and show in what way Benford’s law can be used in fraud detection.
The room is 1.050, on the first floor of the building Maison du Nombre. You can find here a map of Campus Belval.
A sandwich lunch will be provided to all participants. Your preferences have been collected in the registration survey.
datascienceschool@uni.lu