Stud.IP Uni Oldenburg
Universität Oldenburg
08.12.2021 08:33:15
phy694 - Machine Learning II (Vollständige Modulbeschreibung)
Originalfassung Englisch PDF Download
Modulbezeichnung Machine Learning II
Modulkürzel phy694
Kreditpunkte 6.0 KP
Workload 180 h
(
Attendance: 56 hrs, Self study: 124 hrs
)
Einrichtungsverzeichnis Institut für Physik
Verwendbarkeit des Moduls
  • Master Engineering Physics (Master) > Schwerpunkt: Acoustics
Zuständige Personen
Lücke, Jörg (Prüfungsberechtigt)
Lücke, Jörg (Modulverantwortung)
Teilnahmevoraussetzungen
The course requires the introductory course “Machine Learning – Probabilistic Unsupervised Learning” or equivalent courses.
Kompetenzziele
The students will deepen their knowledge on mathematical models of data and sensory signals. Building upon the previously acquired Machine Learning models and methods, the students will be lead closer to current research topics and will learn about models that currently represent the state-of-the-art. Based on these models, the students will be exposed to the typical theoretical and practical challenges in the development of current Machine Learning algorithms. Typical challenges are analytical and computational intractabilities, or local optima problems. Based on concrete examples, the students will learn how to address such problems. Applications to different data will teach skills to use the appropriate model for a desired task and the ability to interpret an algorithm’s result as well as ways for further improvements. Furthermore, the students will learn interpretations of biological and artificial intelligence based on state-of-the-art Machine Learning models.
Modulinhalte
This course builds up on the basic models and methods introduced in introductory Machine Learning lectures. Advanced Machine Learning models will be introduced alongside methods for efficient parameter optimization. Analytical approximations for computationally intractable models will be defined and discussed as well as stochastic (Monte Carlo) approximations. Advantages of different approximations will be contrasted with their potential disadvantages. Advanced models in the lecture will include models for clustering, classification, recognition, denoising, compression, dimensionality reduction, deep learning, tracking etc. Typical application domains will be general pattern recognition, computational neuroscience and sensory data models including computer hearing and computer vision.
Literaturempfehlungen

Pattern Recognition and Machine Learning, C. M. Bishop, Springer 2006. (best suited for lecture).;

Information Theory, Inference, and Learning Algorithms, D. MacKay, Cambridge University Press, 2003. (free online)
Links
Unterrichtssprache Englisch
Dauer in Semestern 1 Semester
Angebotsrhythmus Modul jährlich
Aufnahmekapazität Modul unbegrenzt
Modullevel / module level MM (Mastermodul / Master module)
Modulart / typ of module Wahlpflicht / Elective
Lehr-/Lernform / Teaching/Learning method Lecture: 2hrs/week, Exercise: 2hrs/week (incl. prog. laboratory)
Vorkenntnisse / Previous knowledge Basic knowledge in higher Mathematics taught as part of first degrees in Physics, Mathematics, Statistics, Engineering or Computer Science (basic linear algebra and analysis) is required. Additionally, programming skills are required (Matlab or python).
Prüfung Prüfungszeiten Prüfungsform
Gesamtmodul
Max. 180 min. Klausur oder 30 min. mündliche Prüfung
Lehrveranstaltungsform Vorlesung
SWS 4
Angebotsrhythmus SoSe oder WiSe
Workload Präsenzzeit 56 h