Module Handbook

  • Dynamischer Default-Fachbereich geändert auf MV

Notes on the module handbook of the department Mechanical and Process Engineering

Die hier dargestellten veröffentlichten Studiengang-, Modul- und Kursdaten des Fachbereichs Maschinenbau und Verfahrenstechnik ersetzen die Modulbeschreibungen im KIS und wuden mit Ausnahme folgender Studiengänge am 28.10.2020 verabschiedet.

Ausnahmen:

Module MV-MEC-M193-M-7

Machine Learning (M, 5.0 LP)

Module Identification

Module Number Module Name CP (Effort)
MV-MEC-M193-M-7 Machine Learning 5.0 CP (150 h)

Basedata

CP, Effort 5.0 CP = 150 h
Position of the semester 1 Sem. in SuSe
Level [7] Master (Advanced)
Language [EN] English
Module Manager
Bajcinca, Naim, Prof. Dr.-Ing. (PROF | DEPT: MV)
Lecturers
Bajcinca, Naim, Prof. Dr.-Ing. (PROF | DEPT: MV)
Area of study [MV-MEC] Mechatronics in Mechanical and Automotive Engineering
Reference course of study [MV-88.808-SG] M.Sc. Computational Engineering
Livecycle-State [NORM] Active

Courses

Type/SWS Course Number Title Choice in
Module-Part 		Presence-Time /
Self-Study 		SL SL is
required for exa. 		PL CP Sem.
2V+1U MV-MEC-86692-K-7
Machine Learning
P 42 h 108 h - - PL1 5.0 SuSe
  • About [MV-MEC-86692-K-7]: Title: "Machine Learning"; Presence-Time: 42 h; Self-Study: 108 h

Examination achievement PL1

  • Form of examination: oral examination (30-45 Min.)
  • Examination Frequency: each semester
  • Examination number: 10692 ("Machine Learning")

Evaluation of grades

The grade of the module examination is also the module grade.


Contents

From [MV-MEC-86692-K-7] Machine Learning:
  • Bayes classifiers.
  • Logistic regression.
  • Perceptron.
  • Support vector machines.
  • Clustering.
  • Factor analysis.
  • Neural networks architecture.
  • Forward- and backpropagation.
  • Markov decision processes.
  • Bellman equations.
  • Deep Q-learning.

Competencies / intended learning achievements

From [MV-MEC-86692-K-7] Machine Learning:
1. Lecture:

Machine learning plays an important role in a variety of applications such as data mining, natural language processing, image recognition, expert systems, and autonomous driving. The lecture provides an overview of the basic concepts, techniques, and algorithms of modern machine learning. It also aims to provide rigorous mathematical foundations of the methods covered.

2. Exercise:

Students will get hands-on experience in applying machine learning algorithms on real life problems.

Literature

From [MV-MEC-86692-K-7] Machine Learning:
  • Murphy, K.: “Machine Learning: A probabilistic perspective”. Adaptive Computation and Machine Learning Series. The MIT Press, 2012.
  • Sutton, R.S., Barto, A.G.: “Reinforcement Learning: An introduction”. Cambridge: MIT Press, 1998.
  • Goodfellow I., Bengio Y., Courville A.: “Deep Learning”. Cambridge: MIT Press, 2016.
  • Hastie, T., Tibshirani, R., Friedman, J.:“The Elements of Statistical Learning: Data Mining, Inference, and Prediction”. Springer Series in Statistics, Springer, 2016.

Requirements for attendance (informal)

Lectures on higher mathematics

Requirements for attendance (formal)

None

References to Module / Module Number [MV-MEC-M193-M-7]

Module-Pool Name
[MV-ALL-MPOOL-6] Wahlpflichtmodule allgemein
[MV-CE-MPOOL-6] Wahlpflichtmodule Computational Engineering
[MV-MBINFO-MPOOL-6] Wahlpflichtmodule Maschinenbau mit angewandter Informatik