phy730 - Machine Learning (Course overview)

phy730 - Machine Learning (Course overview)

Institute of Physics 6 KP
Module components Semester courses Wintersemester 2021/2022 Examination
Lecture
  • No access 5.04.4213 - Machine Learning I - Probabilistic Unsupervised Learning Show lecturers
    • Prof. Dr. Jörg Lücke

    Wednesday: 10:15 - 11:45, weekly (from 20/10/21), Location: W32 0-005
    Dates on Tuesday, 08.03.2022 - Friday, 11.03.2022 08:30 - 18:30, Monday, 14.03.2022 08:30 - 16:00, Tuesday, 15.03.2022 08:30 - 13:00, Monday, 30.05.2022 11:00 - 18:00, Tuesday, 31.05.2022 08:00 - 18:00, Location: W01 0-012, W04 1-171

    The field of Machine Learning develops and provides methods for the analysis of data and signals. Typical application domains are computer hearing, computer vision, general pattern recognition and large-scale data analysis (recently often termed "Big Data"). Furthermore, Machine Learning methods serve as models for information processing and learning in humans and animals, and are often considered as part of artificial intelligence approaches. This course gives an 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. The course requires some programming skills, preferably in Matlab or Python. Further requirements are typical mathematical / analytical skills that are taught as part of Bachelor degrees in Physics, Mathematics, Statistics, Computer and Engineering Sciences. Course assignments will include analytical tasks and programming task which can be worked out in small groups. The presented approach to unsupervised learning relies on Bayes' theorem and is therefore sometimes referred to as a Bayesian approach. It has many interesting relations to physics (e.g., statistical physics), statistics and mathematics (analysis, probability theory, stochastic) but the course's content will be developed independently of detailed prior knowledge in these fields. Weblink: www.uni-oldenburg.de/ml

Exercises
  • No access 5.04.4213 - Machine Learning I - Probabilistic Unsupervised Learning Show lecturers
    • Prof. Dr. Jörg Lücke

    Wednesday: 10:15 - 11:45, weekly (from 20/10/21), Location: W32 0-005
    Dates on Tuesday, 08.03.2022 - Friday, 11.03.2022 08:30 - 18:30, Monday, 14.03.2022 08:30 - 16:00, Tuesday, 15.03.2022 08:30 - 13:00, Monday, 30.05.2022 11:00 - 18:00, Tuesday, 31.05.2022 08:00 - 18:00, Location: W01 0-012, W04 1-171

    The field of Machine Learning develops and provides methods for the analysis of data and signals. Typical application domains are computer hearing, computer vision, general pattern recognition and large-scale data analysis (recently often termed "Big Data"). Furthermore, Machine Learning methods serve as models for information processing and learning in humans and animals, and are often considered as part of artificial intelligence approaches. This course gives an 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. The course requires some programming skills, preferably in Matlab or Python. Further requirements are typical mathematical / analytical skills that are taught as part of Bachelor degrees in Physics, Mathematics, Statistics, Computer and Engineering Sciences. Course assignments will include analytical tasks and programming task which can be worked out in small groups. The presented approach to unsupervised learning relies on Bayes' theorem and is therefore sometimes referred to as a Bayesian approach. It has many interesting relations to physics (e.g., statistical physics), statistics and mathematics (analysis, probability theory, stochastic) but the course's content will be developed independently of detailed prior knowledge in these fields. Weblink: www.uni-oldenburg.de/ml

  • No access 5.04.4213 Ü1 - Machine Learning I - Probabilistic Unsupervised Learning Show lecturers
    • Prof. Dr. Jörg Lücke
    • Florian Hirschberger
    • Filippos Panagiotou

    Tuesday: 16:15 - 17:45, weekly (from 26/10/21), Location: W32 0-005, W32 1-112

  • No access 5.04.4213 Ü2 - Machine Learning I - Probabilistic Unsupervised Learning Show lecturers
    • Prof. Dr. Jörg Lücke
    • Filippos Panagiotou
    • Florian Hirschberger

    Tuesday: 16:15 - 17:45, weekly (from 26/10/21)

  • No access 5.04.4213 Ü3 - Machine Learning I - Probabilistic Unsupervised Learning Show lecturers
    • Prof. Dr. Jörg Lücke
    • Dmytro Velychko

    Tuesday: 10:15 - 11:45, weekly (from 26/10/21), Location: W04 1-172, W01 0-012

Notes on the module
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.
Module examination
Klausur (max 180 Min.) oder mündliche Prüfung (30 Min.)
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.