Stud.IP Uni Oldenburg
University of Oldenburg
15.10.2021 22:06:14
phy730 - Machine Learning (Complete module description)
Original version English Download as PDF
Module label Machine Learning
Module code phy730
Credit points 6.0 KP
Workload 180 h
(
Präsenzzeit: 56 Stunden Selbststudium: 124 Stunden
)
Institute directory Institute of Physics
Applicability of the module
  • Master's Programme Engineering Physics (Master) > Schwerpunkt: Acoustics
  • Master's Programme Physics, Engineering and Medicine (Master) > Mastermodule
Responsible persons
Lücke, Jörg (Authorized examiners)
Anemüller, Jörn (Authorized examiners)
Hohmann, Volker (Authorized examiners)
Meyer, Bernd (Authorized examiners)
Prerequisites
Basic knowledge in higher Mathematics as taught as part of first degrees in Physics, Mathematics, Statistics, Engineering or Computer Science (basic linear algebra and analysis). Basic programming skills (course supports matlab & python). Many relations to statistical physics, statistics, probability theory, stochastic but the course's content will be developed independently of detailed prior knowledge in these fields.
Skills to be acquired in this module
The students will acquire advanced knowledge about mathematical models of data and ensory signals, and they will learn how such models can be used to derive algorithms for data and signal processing. They will learn the typical scientific challenges associated with algorithms for unsupervised knowledge extraction including, clustering, dimensionality reduction, compression and signal enhancements. Typical examples will include applications to computer vision and computer hearing. Furthermore, the students will learn modern interpretations of neural learning and neural perception based on probabilistic data models.
Module contents
Introduction to unsupervised learning methods, i.e., methods that extract knowledge from data without the requirement of explicit knowledge about individual data points. We will introduce a common probabilistic framework for learning and a methodology to derive learning algorithms for different types of tasks. Examples that are derived are algorithms for clustering, classification, component extraction, feature learning, blind source separation and dimensionality reduction. Relations to neural network models and learning in biological systems will be discussed were appropriate.
Reader's advisory
 C. M. Bishop, Pattern Recognition and Machine Learning, Springer 2006 (best suited for lecture).  K. P. Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.  D. MacKay, Information Theory, Inference, and Learning Algorithms, Cambridge University Press, 2003 (free online)  K. Petersen, M. Pederson, The Matrix Cookbook, (free online)
Links
Language of instruction English
Duration (semesters) 1 Semester
Module frequency
Module capacity unlimited
Modullevel / module level MM (Mastermodul / Master module)
Modulart / typ of module Pflicht / Mandatory
Lehr-/Lernform / Teaching/Learning method Vorlesung: 2 SWS, Übungen: 2 SWS
Vorkenntnisse / Previous knowledge
Course type Comment SWS Frequency Workload of compulsory attendance
Lecture
2 WiSe 28
Exercises
2 WiSe 28
Total time of attendance for the module 56 h
Examination Time of examination Type of examination
Final exam of module
Klausur (max 180 Min.) oder mündliche Prüfung (30 Min.)