Neural Networks and Learning Theory
Neuronale Netze und Lerntheorie
8 LPSoSe (gerade Jahre)EN
Voraussetzungen
Zwingend, im Wortlaut
No successful participation in associated phase-out module 12450 Neuronale Netze und Lerntheorie.
Empfohlen, im Wortlaut
Basic knowledge both concerning optimality criteria in differentiable optimization and probability theory are advisable, but will be treated briefly in the course. Solid knowledge of the content of module • 11213: Mathematik IT -3 (Analysis)
Inhalte
Some central network architectures are treated. These architectures differ in the way they manipulate input data, the way they perform learning tasks and the analysis of corresponding algorithms by mathematical means. More precisely, the following types of networks are covered: • General aspects of architecures, in particular feedforward nets, recurrent nets • Perceptron network, perceptron learning algorithm • Backpropagation algorithm • Radial basis function networks • Support Vector Machines • Learning theory and Vapnik-Chervonenkis dimension • Self-organizing networks • Hopfield networks Special emphasis will be given to the mathematical analysis of algorithms. This will make it necessary to study some basic facts of optimization and probability theory.
Lernziele
Students will get insight into different network architectures and their principles of operation. Notions like artificial intelligence and automatic learning will be made precise during the course. A central issue is the understanding of mathematical ideas underlying different network learning algorithms. This includes both positive solutions of problems and knowledge about limits of the approaches studied.
Prüfungsleistung
Prerequisite: • Successful completion of homework (fortnightly) and/or successful completion of tests (approx. 4 tests of 15-30 minutes each, written during the lecture period) Final module examination: • Written examination, 90 min. OR • Oral examination, 30-45 min. (with small number of participants) In the first lecture it will be announced, if the examination will be offered in written or oral form.
Literatur (10)
- E. Alpaydin: Maschinelles Lernen, Oldenbourg Verlag München, 2008
- 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, 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, Springer 1996
- S. Shalev-Shwartz, S. Ben-David: Understanding Machine Learning, Cambridge University Press 2014.
Bemerkungen
• Study programme Informatik M.Sc.: Compulsory elective module in complex „Grundlagen der Informatik" (level 400) • Study programme Cyber Security M.Sc.: Compulsory elective module in complex „Computer Science" • Study programme Artificial Intelligence M.Sc.: Compulsory elective module in complex „Learning and Reasoning“ • Study programme Künstliche Intelligenz Technologie M.Sc.: Compulsory elective module in complex „Kognitions- und Neurowissenschaft“ • Study programme Angewandte Mathematik M.Sc.: Compulsory elective module in complex „Analysis / Algebra / Kombinatorik“ • Study programme Mathematik B.Sc.: Compulsory elective module in complex „Vertiefung“, in limited extend • Study programme Wirtschaftsmathematik B.Sc.: Compulsory elective module in complex „Vertiefung“, in limited extend • Study programme Physics M.Sc.: Compulsory elective module in complex „Minor Subject“ • Study programme Mathematical Data Science M.Sc.: Compulsory elective module in complex „Advanced Mathematical Methods in Data Science“
Quelle: Modulbeschreibung der BTU · abgerufen 28.09.2026Original