Module 11847

As usual for all modules at BTU, you have to register online for the module. Since there is a restriction concerning the number of participants, the online registration has to be done before the lecture period starts, i.e., in the period between March, 30th 2026  and April, 12th 2026.

We shall then afterwards decide who will be admitted, see below. Please pay attention to the difference between the official online registration for a module (described above) and the registration in Moodle. The latter is only for organizational purposes during the run of the course. You can register in Moodle for the module following this link. Only the online registration counts as official registration for participating later on in the exam.

This info refers foremost to students from the AI program. Previous experience has shown that many of you register but then do not show up. This behaviour will prevent other seriously interested students from attending the module. Given the previous experiences we shall in a first round try not to kick out students, relying on only a moderate number of really interested students. Therefore please only register when you really intend to attend the entire module and to participate in the exam. Note also that this is a very mathematically oriented module (see below).  Only if this does not work and there will show up significantly more participants than we can manage, we shall apply the official rules to select those students which can attend.

Note also that even though there is no formal requirement of being present in the lectures, it is unavoidable to attend both the lectures and the exercise sessions actively in order to have any realistic chances of passing the exam. There will be several small tests written during some of the lectures, and those you have to pass in order to be admitted to the exam, see both the information in the module description and given in the lectures. 

Though there are no formal prerequisites for the module, I would like to stress that this will be a module which is focussing on the mathematical aspects of neural networks and learning. This means that you should have at least a well-grounded knowledge of basic mathematics as being typical for an undergraduate program in Computer Science. The latter includes proficiency in basic calculus (such as multivariate differential calculus, optimality conditions etc.), linear algebra (algebraic description of geometric objects like hyperplanes, distances, solving linear systems etc.), and basic probability theory. Necessary results will be recalled briefly, but not to the extent that you can learn it for the first time. If you have no such basic knowledge, the module likely will not be suitable for you. 

• E. Alpaydin: Maschinelles Lernen (in German),Oldenbourg Verlag München, 2008
• C.C. Aggarwal: Neural Networks and Deep Learning, Springer, 2018.
• M. Anthony, N.Biggs: Computational Learning Theory, Cambridge University Press 1997
• N. Christiani, J. Shawe-Taylor: An Introduction to Support Vector Machines and kernel-based Learning Methods, Cambridge Univ. Press,  2003
• A.C.C Coolen, R. Kühn, P. Sollich: Theory of Neural Information Processing Systems, Oxford University Press 2005
• P. Fischer: Algorithmisches Lernen (in German), Teubner 1999
• P. Flach: Machine Learning: The Art and Science of Algorithms that Make Sense of Data, Cambridge University Press 2012
• F. M. Ham, I. Kostanic: Principles of Neurocomputing for Science & Engineering, McGraw Hill 2001
• S. Haykin: Neural Networks, Prentice Hall, 1999
• R. Rojas: Theorie der neuronalen Netze (in German), Springer 1996
• S. Shalev-Shwartz, S. Ben-David: Understanding Machine Learning, Cambridge University Press 2014.

Some journals/conferences (thought as appetizer):

• Machine Learning, Springer
• Neural Networks, INNS, Elsevier
• Transactions on Neural Networks, IEEE   
• Association for Computational Learning