Deep Learning (english) - Interactive curriculae of TU Ilmenau

The interactive curriculae provide information on the degree programmes offered by the TU Ilmenau.

Please refer to the respective study and examination rules and regulations for the legally binding curricula (Annex Curriculum).

You can find all details on planned lectures and classes in the course catalogue.

Please note that this page is no longer updated. All modules and study plans from PO version 2021 onwards (Bachelor and Master study programs) are now available on the Campus Portal.

module properties Deep Learning (englisch) in degree program Master Informatik 2013
module name	Deep Learning (englisch)
module number	101969
department	Department of Computer Science and Automation
ID of group	2234 (Software Engineering for safety-critical Systems)
module leader	Prof. Dr. Patrick Mäder
credit points	5
obligation	elective module
requirements
certificate of the module	Individual achievements or exams
details of the certificate
link to Moodle course
teacher
signup details for alternative examinations
learning outcome	Theory: (evaluation by written exam) Knowledge on theoretical foundations of deep neural networks Knowledge on CNN architectures and applications Knowledge on architectures for sequence modeling and their applications Practice: (evaluation by practical assignments) Ability to implement and apply of a variety of deep learning algorithms Ability to evaluate and troubleshoot deep learning models Ability to use computational resources for train and application of deep learning models
The module contains the following subjects:
Deep Learning
credit points	0
obligation	elective module
certificate of the module	examination performance with multiple performances
term	ganzjährig

module properties Deep Learning (english) in degree program unassigned ATTENTION: not offered anymore
module name	Deep Learning (english)
module number	101969
department	Department of Computer Science and Automation
ID of group	2234 (Software Engineering for safety-critical Systems)
module leader	Prof. Dr. Patrick Mäder
credit points	5
obligation	obligatory module
requirements
certificate of the module	alternative examination performance
details of the certificate	The aPl examination consists of five individual activities evaluation methodological, practical as well as social skills of the student: (1) First assignment -- issued: May 20th, 2021 and due: May 27th, 2021 -- graded with up to 10 points (2) Second assignment -- issued: June 10th, 2021 and due: June 17th, 2021 -- graded with up to 10 points (3) First-term test -- June 17th 2021 -- graded with up to 25 points (4) Group project -- project mid-term report submission due: July 8th, 2021 -- project report submission due: July 22nd, 2021 -- project pitch video submission due: July 26th, 2021 -- graded with up to 30 points (5) Second-term test -- July 29th, 2021 -- graded with up to 25 points
link to Moodle course
teacher
signup details for alternative examinations
learning outcome	Theory: (evaluation by written exam) Knowledge on theoretical foundations of deep neural networks Knowledge on CNN architectures and applications Knowledge on architectures for sequence modeling and their applications Practice: (evaluation by practical assignments) Ability to implement and apply of a variety of deep learning algorithms Ability to evaluate and troubleshoot deep learning models Ability to use computational resources for train and application of deep learning models