Data Science (DS)
Companies in research and industry use data to safeguard decisions and to offer data-intensive products and services. The competencies required for these processes are summarised under the term Data Science. The analysis of large amounts of data is composed of scalable data management, parallel algorithms, statistical modeling, and secure handling of the complex interaction of various instruments and platforms and is anchored in various disciplines. On the one hand, this lecture is intended to explain to the participants what is expected of future data scientists and on the other hand to give them the skills they need to fulfill these expectations. The methodical knowledge imparted in the course is intended to be a short “how-to” and enable the participants to independently decide when and why certain methods are to be used. Since one of the biggest problems in data analysis is often the wrong question, the lecture will also look at the company perspective to solve typical company problems and ask the right questions for suitable data analysis. The lecture presents concepts and instruments that are needed throughout the entire data science pipeline. In addition to the correct approach, the lecture will discuss the interpretation of the analysis results as well as their visualization and transformation into business models. In the accompanying exercises, presented methods and algorithms will be applied in practice, focusing on web programming, statistics, and the manipulation of data sets.
Overview
The basics include the following topics:
- Supervised Learning
- Ensemble Learning
- Unsupervised Learning
- Neural Networks
- Convolutional Neural Networks
- Graph Neural Networks
- Large Language Models
- Generative Models
- Explainable AI
- Advanced Topics
Organisation
Semester: SoSe 25
Scope: Lecture (2 SWS) and Exercise / project work (2 SWS) / Total 6 CP
Exam: The course includes a module examination consisting of the written examination (120 minutes) and the assessment of the projects. The module grade is composed as follows: 60% written exam, 40% project work. Registration for the exam is done via VIPA or HIS-LSF POS.
Exam Track 1.0: Students can achieve grade 1.0 in their written examination (60%) if they submit a research in progress paper based on their group project work according to the guidelines of WITS. More details in lecture.
Language: English
Moodle: Course page
Lecture
Lecture Starts: tbd
Time: Fridays, 10:15 – 11:45
Place: 0.07, Building B4 1
Exercise
Exercise Starts: tbd
Time: Fridays, 14:15 – 15:45
Place: 0.07, Building B4 1
Lecturer
Univ.-Prof. Dr.-Ing. Wolfgang Maaß
Contact Person
Maxx Richard Rahman (m.rahman@iss.uni-saarland.de)
Dominic Detering (d.detering@iss.uni-saarland.de)
Further Information
All participants can post questions about the current lecture in the “Participant Forum” on moodle platform, which will then be discussed there.