Summer Seminar 2018: Deep Learning (english)

General Information

Contact: Prof. Dr. Dennis Säring

Audience: Bachelor and Master (B_ECom, B_Inf, B_ITE, B_Tinf, B_WInf, B_Minf, B_STec, M_ECom, M_Inf, M_ITS, M_ITE)

The seminar will take place on

     Tuesday, June 5th 2018 at 08:15 a.m., lecture room HS5


Topic Assignement

The preparation meeting introducing the different topics and assigning topics to participants took place on

     Tuesday, January 9th 2017 at 12:30 p.m., lecture room HS6

Participation at this meeting is obligatory to attend the seminar. It is expected that you scan and skim the chapters of your interest in The Deep Learning book (see below)


Based on the Deep Learning Book [1][2] by Goodfellow, Benjio, and Courville and on the top papers in the field of Deep Learning for Medical Application [3] we will work on different aspects of deep learning. During preparation all participants will famliarize with the basics of deep learning and then focus on a selected deep learning topic. These topics are presented in one hour talks. The following topics are available:

  1. Deep Feedforward Networks
  2. Regularization for Deep Learning
  3. Optimization for Training Deep Models
  4. Convolutional Networks
  5. Recurrent and Recursive Nets
  6. Linear Factor Models
  7. Autoencoders
  8. Deep Learning for Medical Applications



Presenting each topic involves

  1. A talk (incl. slide presentation) of about 40 minutes plus 10 minutes time for discussion and methodological feed back. Talks are to be given in english.
  2. A report (english) of approx. 20 pages that summarizes the topic in written form
    Deadline for first draft: 30th May 2018
    Deadline for final version: 15th June 2018 !!!

Participation of attendees at every talk is required. Reasons for not showing up can exclusively be FH internal course conflicts or medical conditions. They still demand compensation. Not participating in two or more talks will result in failing the seminar.



8:15 Introduction      

8:30 - 9:20 - Deep Feedforward Networks (Ohlsen, Lewe)

9:20 - 10:10 - Optimization for Training Deep Models (Kirschte, Moritz)

10:10 - 11:00 - Convolutional Networks (Wernicke, Franz)

Coffee break (10 min.)

11:10 - 12:00 - Recurrent and Recursive Nets (Nayak, Varun)

12:00 - 12:50 - Autoencoders (Hüet, Sven)

Lunch break (40 min.)

13:30 - 14:20 - Efficient Medical Image Parsing  (Lübkemann, Jana)

14:20 - 15:10 - 3D Convolutional Networks (Pawlowski, Marco)

Coffee break (10 min.)

15:20 - 16:10 - CapsNet (Meinl, Rico)

16:10 - 17:00 - DeepXplore (Peemöller, Marco)

17:00 End



Guests are welcome (Please register by email to