Advanced Deep Learning - from CNN to Transformers

Monday 6 - 7:45 pm // Learn to understand and master the mechanisms behind CNN and RNN and apply them in your own project!


Für diesen Kurs kann man keine Teilnahmenbescheinigung erhalten.

Bei ausreichender Teilnahme und Erbringung eines der angebotenen Leistungsnachweise kannst Du ein Leistungszertifikat erwerben.



Our courses are open to all and free of charge for students, pupils, trainees, founders, scientific staff, job seekers, refugees, and pensioners. For employees and self-employed persons, a fee of 200 euros is charged when acquiring a certificate of achievement. Employees and self-employed persons can apply for a scholarship via

What you get

This course is based on the last two courses of the online Coursera Specialization "Deep Learning" provided by (see The instructor is Andrew Ng, co-founder of Coursera, founding lead of the Google Brain Team, and professor in computer science at Stanford University. The specialization is being currently (the 7th of April) updated and it includes even more modern state of the art techniques.

The course will give you the possibility to discuss and learn different topics: starting from convolutional (CNN) neural network to work with image processing, transfer learning to apply the "knowledge" of a huge network to a new task, will go in detail over famous architecture as MobileNet and Unet, recurrent neural network (RNN) for text and sentence processing, and the latest transformer models.

You will be then supported in the creation of a project with your colleagues based on one of these networks during the course.

This course is part of the Machine Learning Degree. Participants of the program for the Machine Learning Degree get preferred access to this course. Find more information on the Machine Learning Degree here.

All needed software and online course content is free. As Germany's first Coursera for Campus partner, will in particular provide you with full access to the Coursera online learning platform.

What you should bring

Since this is an advanced course (the second of a serie), you do need to have previous knowledge. The pace can be fast and we will assume that you already know how neural networks work and you have some experience with creating your own. This is needed to enjoy and understand the course. If you feel you may need some time or help to get your hands on advanced topics, we suggest you follow the first course Deep Learning from Scratch and come here the next semester.

Your application will be granted if you successfully finished the first course. However, you can also participate if you learned a similar content on your own. Also, you should bring sufficient time. During the week you will be expected to work through the assigned online course content and complete home assignments, for which you should calculate 5-8 hours each week. During the course you will also work on a group project, so be sure to allocate some extra hours more to work on that. The project will start after some (3-4) weeks of the course.

In order to receive a certificate of achievement ("Leistungszertifikat"/ ECTS) for this course, active participation is expected, no more than two classes may be missed, and you have to conduct a practice project in a team of 2 to 4 persons. At the end of the course the project has to be presented and a well documented project source code has to be submitted.

Before the first meeting there will be a Semester Kick-Off on April 8. To participate use this link. In the Kick-Off you will meet your course instructor, can ask questions about the participation in the course, and get helpful information to prepare for the start of the course. The attendance at the Kick-Off is not mandatory but recommended for all participants. During the current Coronavirus outbreak, the Kick-Off as well as the course will be streamed online via Zoom.

If you want to learn more about your course lead, check him out here:


Advanced Deep Learning - from CNN to Transformers
Sommersemester 2021
18:00 - 19:45 Uhr


Luca Palmieri