Winter Term 2024/25

All required information and all links to platforms for our courses are collected on this website. Please, do not write individual emails to the teachers, but use the online courses and platforms instead.

 

Bachelor:

Start of the lecture: 22 October 2024; 14:00

This event 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 categorised 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 takes place online. You can find up-to-date information on the course of the event in the Moodle course.

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

Links:

 

Contact Person:

Start of the lecture:

Monday 21.10.2024, 16:15

Start of exercise:

Gruppe 1: 28.10.2024 08:00 AM
Gruppe 2: 28.10.2024 09:00 AM
Gruppe 3: 29.10.2024 08:00 AM
Gruppe 4: 29.10.2024 09:00 AM 
Gruppe 5: 30.10.2024 08:00 AM 
Gruppe 6: 30.10.2024 09:00 AM 

 

The material of the lecture will be taught according to the teaching concept "Flipped Classroom" in the form of videos. Accompanying the videos, there will be weekly live sessions in which Prof. Sick will discuss further questions with you to deepen your understanding. In addition, there is a short summary of the material from the previous week and a preview of the material for the coming week.

The exercise sheets are provided every Monday. The solutions are uploaded one week later after the last exercise. Only presence exercises are offered in which the exercises can be discussed. To be admitted to the exam, students will need to pass a test that will be held in the E-Assessment Centre.

All further information and regular announcements can be found in the corresponding Moodle course.

 

Meeting Information

 

Contact information:

Name: Minh Tuan Pham

E-Mail: stochastik[at]uni-kassel[dot]de

 

Start of the lecture:

18.10.2024 - 08:00 a.m.

 

 

Part 2 of the module "Laboratory C/Embedded Systems" for students on the waiting list. The course will take place in a blended learning format and further information will be provided in the kick-off event on 18 October at 08:00 (c.t.) in the laboratory of the department in presence.

 

Meeting Information

  • 0303c für die Präsenzteile nach Absprache; Panopto-Videos für den Blended-Learning-Teil im moodle-Kurs verfügbar.

    •  

Contact information:

Name: Benjamin Herwig

E-Mail: herwig@uni-kassel.de

 

 

Please note that the event is not free to attend or book! This course will only be offered unscheduled in winter semester 24/25 for students on the waiting list from summer semester 24; the eligible students have already registered for the course in person after having already been requested to do so!

Start of the lecture:

Tuesday 22.10.2024 - 02:00 p.m.

 

In the Intelligent Technical Systems course, we focus on the complete process chain from data recording from the environment around us (sensor technology, voltage conversion, sampling theorem, etc.) to the representation of the data and its (pre-)processing through to the very first steps in the field of machine learning methods and their evaluation. The course takes place in a blended learning format, from the start of the course until the end of the year with one appointment per week (Tuesdays from 14:00 to 16:00) in presence in the laboratory of the department. The lecture offered via Panopto video in the moodle course will be discussed in person during the appointments; the Jupyter notebooks with exercises supplementing the individual lectures will also be discussed during this weekly appointment, if desired. From the new year onwards, in addition to the Tuesday session until the end of the lecture period, practical exercises will take place every Thursday from 14:00 to 18:00, in which we will deal with hardware setups, electronics and the development of actually intelligent technical systems.

 

Meeting Information

  • Room 0303c (IES group Lab)

 

Contact information:

Name: Benjamin Herwig

E-Mail: herwig@uni-kassel.de

 

Master:

Start of the lecture: 22.10.2024; 14:00

 

This event is offered in the form of a conference seminar. Similar to a scientific conference, participants submit their own conference papers, take part in the review of other papers and meet at the end of the semester for a joint workshop in which the results are presented and discussed. Thematically, this conference is categorised 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 takes place online. You can find up-to-date information on the course of the event in the Moodle course. If you are interested, just drop by the introductory event (see moodle).

Links: 

Contact Person:

Start of the lecture:

Monday the 21.10.2024 - 14:15 - 15:45

Start of exercise:

Wednesday the 06.11.2024 - 10:00 - 11:30

 

Meeting Information

  • room 0303c  (IES Lab room)

 

Contact: Huseljic, Denis

E-Mail: dhuseljic[at]uni-kassel[dot]de

 

Start date of lecture:  22.10.2024 - 12:00

Start of the exercise:  will be held as block subsequently

Meeting room: 

  • Lab 0303c 

 

The lecture deals with the basics of pattern recognition in time series (e.g. sensor signals) and spatially distributed data (e.g. in sensor networks). The following topics are discussed, among others: Fundamentals (e.g. segmentation of time series, correlation of data, features for describing temporal/spatial data), distance measurement of time series, clustering/classification, motif recognition, anomaly detection using various techniques (e.g. nearest neighbour, neural networks, support vector machines), various example applications (signature verification, collaborative hazard warning in vehicles, activity recognition, context recognition with smartphones, etc.).

 

Contact person

Name: Dr.Gruhl, Maik Jessulat

E-Mail: cgruhl@uni-kassel.de, mjessulat[at]uni-kassel[dot]de