Win­ter Term 2020/21

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:

Sto­chas­tik in der tech­ni­schen An­wen­dung

Start date of lecture: Monday, 02.11.2020
Start date of exercise : Thursday, 09.11.2020 (expected)

The introductory event and all other meetings will be held via prerecorded videos and the conference system provided by . If you are interested in this course, join the introductory event, the link is listed above.

In­tel­li­gen­te Tech­ni­sche Sys­te­me

Start date of lecture: Monday, 02.11.2020

The lecture as well as the exercise-events will be held digitally. There will be provided videos (for download, no streams) that will accompany and explain the supplied lecture-slides, the organizational procedure, and the exercises. The regular lecture will be completely substituted by these videos. All relevant materials can be found by 02.11.2020 at the moodle-website.

Se­mi­nar Ma­chi­ne Learning (Ba­che­lor)

The introductory event will take place on 02.11.2020 at 16:00.

Meeting-Informationen (Webex):

The introductory event and all other meetings will be held via a conference system. If you are interested in this course, join the introductory event. If you have any question just contact me.

Contact Person:
Florian Heidecker
florian.heidecker[at]uni-kassel[dot]de

Mas­ter:

La­bor De­ep Learning

The introductory event will take place on 05.11.2020 at 14:00.

The conference system of DFN will be used for this purpose. Please register for the course in Moodle, there you will find further instructions on how to participate via DFN. The number of participants may be limited if the number of interested students is too high. A selection will then be made based on previous knowledge. The entire couse will take place digitally.

The event is held in a "flipped classroom" concept. This means that students alternately read a chapter in a selected book and work on exercises. In addition, there are dates for questions and the completion of the exercises. Basic and advanced techniques of deep learning are covered, for example:

  • Basics of PyTorch training using GPUs
  • Simple Deep Neural Network,Convolutional Neural Networks
  • Generative Adversarial Networks
  • Recurrent Neural Networks, Long Short Term Memory
  • Invertable Neural Networks
  • Autoencoder, Variational Autoencoder

At the end of the course, the gained knowledge will be applied to a project in a technical application such as Computer Vision or other current research topics.

Pat­tern Re­co­gni­ti­on and Ma­chi­ne Learning I

Start of the exercise: Wednesday 04.11.2020 (expected)

Both the lecture and the exercises take place digitally. The conference system of DFN is used for this purpose. Please register for the Moodle-Kurs, where you will find further instructions regarding participation via DFN.

The lecture covers the foundations of pattern recognition from a probabilistic point of view. The following topics are discussed:

  • Basics (e.g., stochastics, model selection, Curse of Dimensionality, decision and information theory)
  • Distributions (e.g., multinomial, Dirichlet, Gaussian and Student distributions, nonparametric estimation)
  • Linear models for regression
  • Linear models for classification
  • Neural networks
  • Kernel methods

Se­mi­nar (Mas­ter) in­cl. Se­mi­nar Smart Me­cha­tro­nic Sys­tems

The introductory event will take place on 02.11.2020 at 16:00.

Meeting-Information (Webex):

The introductory event and all other meetings will be held via a conference system. If you are interested in this course, join the introductory event, the link is listed below. If you have any question just contact me.

Contact Person:
Florian Heidecker
florian.heidecker[at]uni-kassel[dot]de

Pro­jekt (Ba­che­lor)

Pro­ject (Mas­ter)