Time only SS
Time Thursday, 8.15h-9.45h
Room 136
Credits 2 SWS / 5 ECTS
Exam Paper and Presentation


  • First lesson in term SS 19: 21.03.2019
  • First presentations: Literature study and state of the art: 11.04.2019
  • Ethics in AI, Clarissa Henning, 06.06.2019
  • Final presentation: t.b.d.

Prerequisites for participation

  • Successful completion of either the CSM Machine Learning Lecture or the CSM Object Recognition Lecture

Resources and Presentations


  1. In the first part of the term (approx. 6 weeks) a bunch of currently hot Deep Learning topics is proposed. For example

    • Deep Neural Networks for Natural Language Processing, e.g. text-classification, question-answering, language-modelling, machine-translation, …
    • BERT and GPT-2 for automatic text generation
    • Generative Adversarial Networks (GANs), for e.g. image generation and modification
    • Main current research challenges in Deep Learning, e.g. explainability, confidence, transfer-learning, integration of domain-knowledge, …
  2. In the second part of the term, student-groups select one current topic of Deep Learning and analyse this topic in depth.

  3. A topic can be a concrete paper

  4. There should be 2-4 students per group

  5. Each group studies the selected topic during the term. This study includes the following:

    1. Literarure Research:
      1. Determine the most important papers and approaches for the selected topic
      2. Which approaches do they apply? How do they differ and how are they related to each other?
      3. What is the impact of the paper (on other scientific work or applications)
      4. Presentation of literature-research
    2. Select a main paper for the topic:
      1. Understand and investigate the approach of the selected paper in detail
      2. Presentation of the technique (in detail) at the end of this course
    3. Reimplement the experiment of the selected paper and reconstruct its result
    4. Suggest modificications and improvements, implement and validate/evaluate them
    5. Final Presentation

List of potential topics to investigate

Deep Neural Networks for Language Understanding:

Explainable AI and Causality

Style Transfer Networks

Low-Resource-Learning / Transfer Learning / Active Learning

AlphaGo / AlphaZero / AlphaStar