Course Content & Topics
Theoretical and practical aspects of computing and learning with neural networks. Examination of the most commonly used algorithms for deep learning. From a practical point of view, different learning algorithms and types of neural networks are implemented and applied to artificial and real-world problems.
Initially, the selected methods are developed in 5-6 lecture units. Students then select a machine learning method and apply it independently. The project work is accompanied by weekly tutorials with tips and tricks. Finally, the project results are discussed in a written report and finally presented for 10-15 minutes. The grade is based on the quality of the code, the report and the final short presentation.
Learning Objectives
After successfully completing the integrated course, students will be able to:
- describe and apply basic concepts and commonly used architectures of deep learning.
- explain in detail how deep neural networks are designed and trained in supervised and unsupervised learning scenarios.
- describe the advantages of different neural network models and algorithms, as well as their relationship to important machine learning concepts such as generalization and regularization.
- apply the acquired practical skills in the implementation and application of state-of-the-art deep learning methods to solve various problems.
Location & Time
Location: TBD. Starting in November, lectures are planned to be held in HS 3 Studienzentrum (35SZ02211).
Time: TBD.
Grading
Immanent examination character. Details will be presented in the first lecture unit.
* Active participation: 0-10 bonus points for active participation.
* Task sheets: 0-30 points for independent work on theoretical aspects.
* Project submissions:
– The implementation (Python code) will be graded 0-30 points.
– The report is assessed with 0-20 points.
– The slides, the final presentation and the discussion are awarded 0-20 points.
* Grading scale: 0-49.9 points (5), 50-65.9 points (4),66-79 points (3), 80-91 points (2), 92-100 points (1)
(With an overall result of up to 79%, an additional oral performance review MAY (!) also be prescribed if the positive performance record is not clear. In this case, you will be informed as soon as the grades are released. If you have already received a grade via MU online, you will not be invited to another oral examination).
Prerequisites
Formal prerequisites: Good Python programming skills, basics of probability theory, basic algebra and vector calculus, basic knowledge of machine learning.
Recommended prerequisites: Introduction to Machine Learning (“190.018”).
Literature
– Ian Goodfellow, Yoshua Bengio and Aaron Courville, “Deep Learning”, 2016.
– Christopher M Bishop, “Pattern Recognition and Machine Learning”, 2006.
