Summer semester 2025

The content on this page was translated automatically.

All necessary information and links to courses in the summer semester can be found on this page, organized by course. Please ask all questions to the lecturers in the courses or via the platforms used in each case - not in individual emails to the lecturers.

Bachelor:

Start of the lecture: 25.04.2025; 10:00

Start of the exercise: 25.04.2025; 12:00

  • Room 1418 (10:00 - 12:00)

  • Room 0425 (12:00 - 14:00)

Course description

Soft computing is an interdisciplinary field of computer science that combines various methods and techniques to solve complex problems that cannot be solved effectively or efficiently using conventional, deterministic approaches. Soft computing is based on the use of fuzzy, probabilistic and evolutionary methods to process uncertain and incomplete information and make decisions. The lecture Soft Computing covers various topics, such as fuzzy logic, neural networks (incl. deep learning) and evolutionary algorithms.

Exercises and lectures are mixed.

Contact person:

Links:

Start of the course: 29.04.2025 12:00 in room -1607

 

Algorithms in the field of data science from technical applications; focus on regression and classification techniques; basics and data preprocessing; feature selection; linear models for regression and classifiers (e.g. linear balancing problem, perceptron learning, Fisher criterion); evaluation; non-linear models for regression and classification (e.g. support vector machines, decision trees); ensemble techniques; basics of modeling with dynamic models.

 

This course takes place in presence.

Registration and further information will be administered via Moodle.

Contact persons:

Start of the course: The seminar starts in week 18. For further information see Moodle course.

Content:

This course is offered in the form of a conference seminar. Similar to a scientific conference, the participants submit their own conference contributions, participate in the review of other contributions and meet at the end of the semester for a joint workshop in which the results obtained are presented and discussed. Thematically, this conference is in the field of machine learning. The specific topics of the seminar papers are announced by academic staff from the department and presented at the introductory event. This takes place at the beginning of the lecture period.

The introductory event is expected to take place in person. You can find up-to-date information about the course in the Moodle course.

If you are interested, just drop by the introductory event (see moodle).

Links:

Contact persons:

Master:

Dates for the start of the course
Start of the lecture: 13.04.2025 - 10:00
Start of the exercise: 25.04.2025 - 10:00


Description: The Experimentation and Evaluation in Machine Learning (E2ML) course provides a basic overview of the scientific method in the context of machine learning research, i.e., from formulating research questions to planning and conducting experiments to analyzing and reporting the results. For this purpose, common methods of machine learning, experimentation and evaluation are discussed.

Lecture and exercise take place in the IES lab WA73 Lab 0303c-FB16-IES.

 

Contact person:


Marek Herde(marek.herde[at]uni-kassel[dot]de)

 

Start of the course: 23.04.2025 : 12:00 - 14:00 in room - 0303c

 

This semester, the Deep Learning lab will focus on state-of-the-art models in the field of autonomous driving for the detection of objects and infrastructure in road traffic (cars, pedestrians, road markings, ...). In the first part of the course we offer a combination of lecture and self-study. This provides the theoretical basis for the second half of the course. In the second half, small groups will work on selected challenges in the field of autonomous driving.

 

 

This course takes place in presence.

Registration and further information will be managed via Moodle.

Contact persons:

Start of the event: 23.04.2025: 12:00 - 14:00 in room - 0303c

 

This semester, the Intelligent Robots lab is about state-of-the-art in the field of autonomous driving to solve problems in road traffic (object detection, route planning, ...). In the first part of the course we offer a combination of lecture and self-study. This provides the theoretical basis for the second half of the course. In the second half, small groups will work on selected challenges in the field of autonomous driving.

 

 

This course takes place in presence.

Registration and further information will be managed via Moodle.

Contact persons:

Dates for the start of the course
Start of the lecture: 24.04.2025:10:00 - 12:00
Start of the exercise: 29.04.2025: 8:00 - 10:00


Description: This course provides an introduction to methods that enable intelligent systems to learn and adapt autonomously. Key topics covered include reinforcement learning, self-supervised learning and transfer learning, as well as active and collaborative learning. It also looks at concepts of self-awareness in AI systems and shows how learning can be improved through interaction and experience. The focus is on methods that require minimal supervision and enable generalization across different tasks.

Lecture and exercise take place in the IES lab WA73 Lab 0303c-FB16-IES.

 

Contact person:


Prof. Dr. Bernhard Sick(bsick@uni-kassel.de)

Start of the course: The seminar starts in week 18. For further information see Moodle course.

Content:

This course is offered in the form of a conference seminar. Similar to a scientific conference, the participants submit their own conference contributions, participate in the review of other contributions and meet at the end of the semester for a joint workshop in which the results obtained are presented and discussed. Thematically, this conference is in the field of machine learning. The specific topics of the seminar papers are announced by academic staff from the department and presented at the introductory event. This takes place at the beginning of the lecture period.

The introductory event is expected to take place in person. You can find up-to-date information about the course in the Moodle course.

If you are interested, just drop by the introductory event (see moodle).

Links:

Contact persons: