|
Mathematical Methods for Machine Learning and Signal Processing (MMMLSP)5 ECTS (englische Bezeichnung: Mathematical Methods for Machine Learning and Signal Processing)
Modulverantwortliche/r: Veniamin Morgenshtern Lehrende:
Veniamin Morgenshtern
Start semester: |
SS 2019 | Duration: |
1 semester | Cycle: |
jährlich (WS) |
Präsenzzeit: |
60 Std. | Eigenstudium: |
90 Std. | Language: |
Englisch |
Lectures:
-
-
Mathematical Methods for Machine Learning and Signal Processing
(Vorlesung, 4 SWS, Veniamin Morgenshtern, Tue, 8:15 - 9:45, 05.025; Thu, 12:15 - 13:45, 05.025)
-
Supplements for Mathematical Methods for Machine Learning and Signal Processing
(Übung, Veniamin Morgenshtern, Thu, 16:15 - 17:45, 05.025)
Inhalt:
This course focuses on modern machine learning and signal processing algorithms that have firm mathematical footing.
First, we will study the basics of Frame Theory -- a mathematical framework for linear redundant signal expansions. We will discuss an applications in signal sampling.
Second, we will study the theory of Compressed Sensing -- a powerful way to recover sparse signals from an incomplete set of measurements.
Third, we will discuss applications of Compressed Sensing-based methods in Machine Learning: Matrix Completion and Subspace Clustering.
Finally, we will study the theory of Scattering Transform -- a signal representation based on deep neural network that is invariant to signal translations and deformations. This topic is one of the few mathematical results related to theoretical understanding of deep learning.
Time permitting, we will discuss other results related to the theoretical understanding of deep learning, such as Tishbi's Information Bottleneck principle.
Lernziele und Kompetenzen:
Students are able to:
Theoretically analyze machine learning and signal processing algorithms.
Develop new complex algorithms.
Do research in the field of modern machine learning and signal processing.
Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan: Das Modul ist im Kontext der folgenden Studienfächer/Vertiefungsrichtungen verwendbar:
- Advanced Signal Processing & Communications Engineering (Master of Science)
(Po-Vers. 2016w | TechFak | Advanced Signal Processing & Communications Engineering (Master of Science) | Gesamtkonto | Wahlpflichtmodule | Technical Mandatory Electives)
- Communications and Multimedia Engineering (Master of Science)
(Po-Vers. 2011 | TechFak | Communications and Multimedia Engineering (Master of Science) | Gesamtkonto | Wahlmodule | Technische Wahlmodule)
Studien-/Prüfungsleistungen:
Mathematical Methods for Machine Learning and Signal Processing (Prüfungsnummer: 887141)
(englischer Titel: Mathematical Methods for Machine Learning and Signal Processing)
- Prüfungsleistung, mündliche Prüfung, Dauer (in Minuten): 30, benotet
- Anteil an der Berechnung der Modulnote: 100.0 %
- Prüfungssprache: Englisch
- Erstablegung: SS 2019, 1. Wdh.: WS 2019/2020
1. Prüfer: | Veniamin Morgenshtern |
|
|
|