IE 678: Deep Learning (FSS 2022)


  • Lecturer:Prof. Dr. Rainer Gemulla, Daniel Ruffinelli
  • Type of course: Lecture (inverted classroom), exercises, assignments (6 ECTS points)
  • Prerequisites: IE 675b Machine Learning or equivalent
  • Registration: enroll in Portal 2

Lecture (Thursday) starts in the first week, tutorial (Tuesday) in the second week. Videos, lecture notes, exercises, assignments, and supplementary material can be found in ILIAS.


Machine learning is concerned with building computer systems that improve with experience as well as the study of learning processes, including the design of algorithms that are able to make predictions or extract knowledge from data. Building upon IE 675b Machine Learning, this course focuses on deep learning and introduces basic and advanced deep learning architectures and techniques, training methods and hyperparameter optimization, as well as selected applications.

Tentative topics include:

  • Feedforward neural networks
  • Training deep learning models
  • Recurrent neural networks
  • Convolutional neural networks
  • Attention and self-attention
  • Deep learning for graphs
  • Deep generative modelling
  • Hyperparameter optimization


  • K.P. Murphy. Machine Learning: A Probabilistic Perspective, The MIT Press, 2012 (4th printing)
  • I. Goodfellow, Y. Bengio, A. Courville. Deep Learning. The MIT Press, 2017 (
  • D. Koller, N. Friedman. Probabilistic graphical models. The MIT Press, 2009
  • Additional material and articles provided in lecture notes