The objective of the Data Challenge courses is to teach students how to perform large-scale data-driven analyses themselves, combining the technical skills acquired earlier with insights gained in methodological courses. As an example, consider creating a classification of real eye scans images for detecting Diabetic Retinopathy (based on a prepared, labeled data set). The challenge in this setting involves training a neural network on the classification task and reflecting the quality of the trained classifier regarding its practical application (should a medical doctor trust the results of a classifier with 80% accuracy).
Cursusperiode1/09/17 → …