623.714 (22S) Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice
Überblick
Weitere Informationen zum Lehrbetrieb vor Ort finden Sie unter: https://www.aau.at/corona.
- Lehrende/r
- LV-Titel englisch Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice
- LV-Art Vorlesung-Kurs (prüfungsimmanente LV )
- LV-Modell Präsenzlehrveranstaltung
- Semesterstunde/n 2.0
- ECTS-Anrechnungspunkte 4.0
- Anmeldungen 21 (30 max.)
- Organisationseinheit
- Unterrichtssprache Englisch
- LV-Beginn 30.05.2022
- eLearning zum Moodle-Kurs
Zeit und Ort
LV-Beschreibung
Intendierte Lernergebnisse
The indented teaching goals can be summarized as follows:
- The students are able to understand the theoretical foundations and how these are related to the practical implementations.
- The students are able to describe and interpret the theoretical foundations.
- The students are able to apply existing tools for pre-defined tasks.
- The students are able to configure/adopt presented methods for different applications of their interest.
Lehrmethodik
- Lecture
- Interactive Training (in the course)
- Practical Assignments (offline, individual training)
Inhalt/e
To cover the overall topics, there will be three blocks:
Block I – Preliminaries:
- Mathematical principals
- Introduction to Python and Tensorflow
Block II – Machine Learning:
- Introduction to Machine Learning
- Machine Learning Paradigms
- Linear Classification and Support Vector Machines
- Decisions Trees and Random Forests
- Neural Networks and Deep Learning
Block III – Practical Applications:
- Medical imaging
- Interpretation of remote sensing data
- Image segmentation and classification
- Interactive ML in practice
- etc.
Erwartete Vorkenntnisse
Mathematical Background:
- Linear Algebra
- Linear and Convex Optimization
Programming Skills:
- Basic Python skills would be beneficial, but are not necessary
Literatur
Pattern Recognition and Machine Learning
- Christopher M. Bishop
- Springer, 2007
- https://link.springer.com/book/9780387310732
The Elements of Statistical Learning
- Trevor Hastie, Robert Tibshirani, and Jerome Friedman
- Springer, 2009
- https://link.springer.com/book/10.1007/978-0-387-84858-7
- Free version available:
An Introduction to Statistical Learning with Applications in R
- Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani
- Springer, 2015
- https://link.springer.com/book/10.1007/978-1-4614-7138-7
- Free version available;
Deep Learning
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville
- MIT Press, 2016
- https://mitpress.mit.edu/books/deep-learning
- Free version available:
Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow
- Aurélien Géron
- O'Reilly, 2019
- https://www.oreilly.com/library/view/hands-on-machine-learning/9781492032632/
Prüfungsinformationen
Prüfungsmethode/n
The are three independent evaluation criteria:
- Written (online) exam: 50%
- Flipped classroom: 10%
- Practical assignment: 40%
Prüfungsinhalt/e
The course content will be recapitulated via flipped classroom sessions, which also defines the content of the exam. The practical assignments are assigned in the end of the course based on the interests of the students.
Beurteilungskriterien/-maßstäbe
The grading can be seen in Moodle at any time, where the following overall scheme will be used:
- Sehr Gut: 92,00% – 100,00%
- Gut: 83,00% – 91,99%
- Befriedigend: 74,00 – 82,99% %
- Genügend: 60,00% – 73,99%
- Nicht Genügend: 0% – 59,99%:
Beurteilungsschema
Note BenotungsschemaPosition im Curriculum
- Doktoratsprogramm Informatics
(SKZ: ---, Version: 17W.1)
-
Fach: Informatics
(Pflichtfach)
-
Informatics (
0.0h XX / 0.0 ECTS)
- 623.714 Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice (2.0h VC / 4.0 ECTS)
-
Informatics (
0.0h XX / 0.0 ECTS)
-
Fach: Informatics
(Pflichtfach)
- Masterstudium Informatics
(SKZ: 911, Version: 19W.2)
-
Fach: Distributed Systems
(Wahlfach)
-
Weitere LVen aus dem gewählten Spezialisierungsfach (
0.0h XX / 12.0 ECTS)
- 623.714 Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice (2.0h VC / 4.0 ECTS) Absolvierung im 1., 2. Semester empfohlen
-
Weitere LVen aus dem gewählten Spezialisierungsfach (
0.0h XX / 12.0 ECTS)
-
Fach: Distributed Systems
(Wahlfach)
- Doktoratsstudium Doktoratsstudium der Technischen Wissenschaften
(SKZ: 700, Version: 18W.1)
-
Fach: Studienleistungen gem. § 3 Abs. 2a des Curriculums
(Pflichtfach)
-
Studienleistungen gem. § 3 Abs. 2a des Curriculums (
0.0h XX / 32.0 ECTS)
- 623.714 Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice (2.0h VC / 4.0 ECTS)
-
Studienleistungen gem. § 3 Abs. 2a des Curriculums (
0.0h XX / 32.0 ECTS)
-
Fach: Studienleistungen gem. § 3 Abs. 2a des Curriculums
(Pflichtfach)
- Doktoratsstudium Doktoratsstudium der Technischen Wissenschaften
(SKZ: 700, Version: 12W.4)
-
Fach: Studienleistungen gem. § 3 Abs. 2a des Curriculums
(Pflichtfach)
-
Studienleistungen gem. § 3 Abs. 2a des Curriculums (
16.0h XX / 32.0 ECTS)
- 623.714 Selected Topics in Distributed Multimedia Systems – Machine Learning: From Theory to Practice (2.0h VC / 4.0 ECTS)
-
Studienleistungen gem. § 3 Abs. 2a des Curriculums (
16.0h XX / 32.0 ECTS)
-
Fach: Studienleistungen gem. § 3 Abs. 2a des Curriculums
(Pflichtfach)