Technische Universität Ilmenau

Deep Learning - Modultafeln of TU Ilmenau

The module lists 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 electronic university catalogue.

Information and guidance on the maintenance of module descriptions by the module officers are provided at Module maintenance.

Please send information on missing or incorrect module descriptions directly to modulkatalog@tu-ilmenau.de.

module properties Deep Learning in degree program Diplom Elektrotechnik und Informationstechnik 2017
module number200131
examination number220488
departmentDepartment of Computer Science and Automation
ID of group 2252 (Computer Graphics)
module leaderProf. Dr. Patrick Mäder
term winter term only
languageEnglisch
credit points5
on-campus program (h)45
self-study (h)105
obligationelective module
examexamination performance with multiple performances
details of the certificate

Das Modul Deep Learning mit der Prüfungsnummer 220488 schließt mit folgenden Leistungen ab:

  • alternative semesterbegleitende Prüfungsleistung mit einer Wichtung von 50% (Prüfungsnummer: 2200822)
  • alternative semesterbegleitende Prüfungsleistung mit einer Wichtung von 50% (Prüfungsnummer: 2200823)

Details zum Abschluss Teilleistung 1:

  • 40% of the partial examination result determined by several assignments evaluating methodological and practical competence in the taught concepts to be solved at home with due date and submission via Moodle
  • the concrete number of assignments will be announced in the early lectures of the course
  • partial result determined as average across submitted solutions to the assignments
  • 60% of the partial examination result will be determined by a group project evaluating competence in applying the taught skills for solving a research problem in a team of peers
  • partial results of the group project will be determined as weighted average across a written project proposal (10%), an interim report (15%), a final report (60%), and a final presentation (15%)
  • students must register via thoska for this exam, typically within the 3rd and 4th week of the semester

 

 Details zum Abschluss Teilleistung 2:

  • written test consisting of multiple choice and free form questions evaluating the professional competence in the topics of the course
  • preferably conducted digitally via Moodle
  • final results may be scaled or individual questions may be excluded depending on best performing percentile of students
alternative examination performance due to COVID-19 regulations incl. technical requirements
signup details for alternative examinations

Mandatory registration for the aPl exams via the central registration system (Thoska) required, typically within the first 2-3 weeks of the semster.

 

For the DL21W course, registration is open till October 31st, 2021.

maximum number of participants
previous knowledge and experience
  • basic programming skills in Python
  • basic understanding of machine learning preferable

learning outcome

Professional competence gained through lectures and examined through written exam:

  • Students have knowledge about theoretical foundations of deep neural networks.
  • Students have knowledge about CNN architectes and their applications.
  • Students have knowledge about architectures for sequence modeling and their applications.


Methodological competence gained through seminars and examined through aPl (assignments):

  • Students gained the ability to implement and apply a variety of deep learning algorithms.
  • Students gained the ability to evaluate and troubleshoot deep learning models.
  • Students gained the ability to use computational resources for training and application of deep learning models.


Social competence gained through lectures and seminars:

  • Students gained insights in ethical aspects of machine learning (e.g., bias, autonomous driving) through discussions in lectures and seminars.
  • Students can discuss advantages and disadvantages of different deep learning approaches among each other and with their lecturers and gained professionality in mastering discussions beyond their mother tongue.
  • Students learn to discuss and solve a scientific problem in a team of peers
content

Deep learning has recently revolutionized a variety of application like speech recognition, image classification, and language translation mostly driven by large tech companies, but increasingly also small and medium-sized companies aim to apply deep learning techniques for solving  an ever increasing variety of problems. This course will give you detailed insight into deep learning, introducing you to the fundamentals as well as to the latest tools and methods in this rapidly emerging field.

Deep learning thereby refers to a subset of machine learning algorithms that analyze data in succeeding stages, each operating on a different representation of the analyzed data. Specific to deep learning is the ability to automatically learn these representations rather than relying on domain expert for defining them manually.

The course will teach you the theoretical foundations of deep neural networks, which will provide you with the understanding necessary for adapting and successfully applying deep learning in your own to implement, parametrize and apply a variety of deep learning (CNNs) as well as recurrent neural networks (RNNs) and transformers for image, text, and time series analysis. You will further become familiar with advanced data science tools and in using computational resources to train and apply deep learning models.

media of instruction and technical requirements for education and examination in case of online participation
  • Presentations
  • Assignments incldung code stubs
  • Jupyter cloud services (personal computer required)
  • All material will be shared via Moodle, accesible [HERE]
literature / references
  • Deep Learning: Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press (2016)

  • Pattern Recognition and Machine Learning: Christoper M. Bishop, Springer (2006)

  • Hands-On Machine Learning with Scikit-Learn and TensorFlow: Aurélien Géron, O'Reilly Media (2017)

evaluation of teaching