- Targeted audience
- Angewandte Informatik Master with 3+1 hours per week and 6 credit points
- Komedia Master with 3+1 hours per week and 6 credit points
- ISE Master with 3+1 hours per week and 6 credit points
|Thursday||12:30 - 15:00||LC/137|
|Thursday||15:00 - 15:45||LC/137||Dr. Ahmet Aker|
As usual, you have to register at the Prüfungsamt for the exams. Normally, you have to do nothing else! Note the type of exam is written exam.
- Introduction: Information Retrieval and Learning to Rank
- Refresher: Concept of Machine Learning
- Introduction: (Artificial) Neural Networks (ANNs)
- Deep Networks: Multi-Layer Perceptron, Tensorflow and Keras, Concept of initialisation and regularization in ANNs
- Advanced Concepts: CNN, RNN, LSTM
- Application: Applying advanced concepts to IR. This part will be based on student assignments where students in groups will apply learned concepts on on-going IR problems and submit their solutions.
- Christopher D. Manning, Prabhakar Raghavan, Hinrich Schütze, Introduction to Information Retrieval. Cambridge University Press, 2008.
- Bruce Croft, Donald Metzler, Trevor Strohman: Search Engines: Information Retrieval in Practice. Addison-Wesley, 2009.
- R. Baeza-Yates, B. Ribeiro-Neto: Modern Information Retrieval. Addison Wesley.
- Marti A. Hearst: Search User Interfaces. Cambridge University Press. (2009)
- Some further IR books and course notes are linked here.
- The Deep Learning lectures are mainly inspired by the following two books:
- Deep Learning with Keras, by Antonio Gulli, Sujit Pal
- Python Machine Learning, by Sebastian Raschka and Vahid Mirjalili (2nd Edition)
Slides as well as sheets for the exercises can be obtained through ILIAS. For this please follow the following steps:
- Shibboleth Login -> Login with your university login information
- Scroll: Magazin -> Information Systems -> 2018 SS Information Retrieval
- Click the button "Beitreten"
- Click the menu item "Folien/Slides"
The goal of these exercises is, that students learn the usage of the concepts, presented in this lecture.
The exercises take place every two weeks.
The sheets for the exercises can be obtained through ILIAS.