Stud.IP Uni Oldenburg
University of Oldenburg
22.09.2021 09:54:58
phy731 - Compulsory Optional Subject Theory (Course overview)
Institute of Physics 6 KP
Module components Semester courses Sommersemester 2021 Examination
Lecture
  • Unlimited access 5.04.4215 - Machine Learning II – Advanced Learning and Inference Methods Show lecturers
    • Prof. Dr. Jörg Lücke

    Thursday: 10:00 - 12:00, weekly (from 15/04/21)
    Dates on Thursday. 29.07.21 - Friday. 30.07.21, Monday. 02.08.21 08:00 - 19:00

    The students will deepen their knowledge on mathematical models of data and sensory signals. Building up on 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 such 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. Contents: 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.

  • Unlimited access 5.04.4586 - Digital Signal Processing Show lecturers
    • Prof. Dr. Simon Doclo

    Monday: 16:00 - 18:00, weekly (from 12/04/21), Location: (online)
    Dates on Thursday. 29.07.21 10:00 - 12:00, Monday. 04.10.21 15:00 - 17:00, Location: A14 1-101 (Hörsaal 1), W32 0-005

    Engineering Physics: Alternative für Signal- und Systemtheorie

Exercises
  • Unlimited access 5.04.4012 Ü1 - Informationsverarbeitung und Kommunikation Show lecturers
    • Dr Jörn Anemüller
    • Eike Jannik Nustede, M. Sc.

    Thursday: 16:00 - 18:00, weekly (from 15/04/21)

    Die Studierenden erlernen, wie statistische Eigenschaften von Signalen zur Lösung von Problemen der Angewandten Physik, insbesondere der Klassifikation, parametrischen Modellierung und Übertragung von Signalen genutzt werden können. Theoretische Lernziele beinhalten damit eine Wiederholung und Festigung statistischer Grundlagen und eine Verständnis von deren Nutzung für Algorithmen unterschiedlicher Zielsetzung und Komplexität. Im praktischen Teil werden Eigenschaften der behandelten Methoden selbständig erarbeitet sowie Algorithmen auf dem Rechner implementiert und auf reale Daten angewendet, so daß der Umgang mit theoretischen Konzepten und ihre praktische Umsetzung erlernt werden. Inhalte: Grundfragen der Informationsverarbeitung (Klassifikation, Regression, Clustering), Lösungsmethoden basierend auf Dichteschätzung und diskriminativen Ansätzen (z.B. Bayes Schätzung, k-nearest neighbour, Hauptkomponentenanalyse, support-vector-machines, Hidden-Markov- Modelle), Grundlagen der Informationstheorie, Methoden der analogen und digitalen Nachrichtenübertragung, Prinzipien der Kanalcodierung und Kompression

  • Unlimited access 5.04.4215 Ü1 - Exercises to Machine Learning II – Advanced Learning and Inference Methods Show lecturers
    • Prof. Dr. Jörg Lücke
    • Florian Hirschberger
    • Filippos Panagiotou
    • Jakob Drefs
    • Seyyed Hamid Mousavi Hashemi

    Tuesday: 14:00 - 16:00, weekly (from 13/04/21), Übung

    The students will deepen their knowledge on mathematical models of data and sensory signals. Building up on 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 such 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. Contents: 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.

  • Unlimited access 5.04.4215 Ü2 - Exercises to Machine Learning II – Advanced Learning and Inference Methods Show lecturers
    • Prof. Dr. Jörg Lücke
    • Filippos Panagiotou
    • Jakob Drefs
    • Seyyed Hamid Mousavi Hashemi
    • Florian Hirschberger

    Thursday: 10:00 - 12:00, weekly (from 15/04/21), Übung

    The students will deepen their knowledge on mathematical models of data and sensory signals. Building up on 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 such 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. Contents: 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.

  • Unlimited access 5.04.4586 Ü1 - Exercises to Digital Signal Processing Show lecturers
    • Daniel Fejgin

    Wednesday: 12:00 - 14:00, weekly (from 21/04/21)

    Engineering Physics: Alternative für Signal- und Systemtheorie

Notes for the module
Prerequisites
Bachelor in Physik, Technik und Medizin oder entsprechender Abschluss
Module examination
M
Skills to be acquired in this module
Theoretische Voraussetzungen für numerische und analytische Modellierung komplexer Vorgänge in der Medizin, Biologie und Biophysik erlangen, um Forschungs-Methoden und -Gegenstände des Exzellenzcluster Hearing4all im Modellierungsbereich anwenden zu können. Spezielle Kompetenzen abhängig von der gewählten Veranstaltung