Suchergebnis: Katalogdaten im Frühjahrssemester 2022

Elektrotechnik und Informationstechnologie Master Information
Master-Studium (Studienreglement 2018)
Signal Processing and Machine Learning
The core courses and specialization courses below are a selection for students who wish to specialize in the area of "Signal Processing and Machine Learning ", see https://www.ee.ethz.ch/studies/main-master/areas-of-specialisation.html.

The individual study plan is subject to the tutor's approval.
Kernfächer
These core courses are particularly recommended for the field of "Signal Processing and Machine Learning".
You may choose core courses form other fields in agreement with your tutor.

A minimum of 24 credits must be obtained from core courses during the MSc EEIT.
Advanced Core Courses
NummerTitelTypECTSUmfangDozierende
227-0427-10LAdvanced Signal Analysis, Modeling, and Machine Learning Information W6 KP4GH.‑A. Loeliger
KurzbeschreibungThe course develops a selection of topics pivoting around state space models, factor graphs, and pertinent algorithms for estimation, model fitting, and learning.
LernzielThe course develops a selection of topics pivoting around state space methods, factor graphs, and pertinent algorithms:
- hidden-Markov models
- factor graphs and message passing algorithms
- linear state space models, Kalman filtering, and recursive least squares
- Gibbs sampling, particle filter
- recursive local polynomial fitting for signal analysis
- parameter learning by expectation maximization
- linear-model fitting beyond least squares: sparsity, Lp-fitting and regularization, jumps
- binary, M-level, and half-plane constraints in control and communications
SkriptLecture notes
Voraussetzungen / BesonderesSolid mathematical foundations (especially in probability, estimation, and linear algebra) as provided by the course "Introduction to Estimation and Machine Learning".
227-0434-10LMathematics of Information Information W8 KP3V + 2U + 2AH. Bölcskei
KurzbeschreibungThe class focuses on mathematical aspects of

1. Information science: Sampling theorems, frame theory, compressed sensing, sparsity, super-resolution, spectrum-blind sampling, subspace algorithms, dimensionality reduction

2. Learning theory: Approximation theory, greedy algorithms, uniform laws of large numbers, Rademacher complexity, Vapnik-Chervonenkis dimension
LernzielThe aim of the class is to familiarize the students with the most commonly used mathematical theories in data science, high-dimensional data analysis, and learning theory. The class consists of the lecture and exercise sessions with homework problems.
InhaltMathematics of Information

1. Signal representations: Frame theory, wavelets, Gabor expansions, sampling theorems, density theorems

2. Sparsity and compressed sensing: Sparse linear models, uncertainty relations in sparse signal recovery, super-resolution, spectrum-blind sampling, subspace algorithms (ESPRIT), estimation in the high-dimensional noisy case, Lasso

3. Dimensionality reduction: Random projections, the Johnson-Lindenstrauss Lemma

Mathematics of Learning

4. Approximation theory: Nonlinear approximation theory, best M-term approximation, greedy algorithms, fundamental limits on compressibility of signal classes, Kolmogorov-Tikhomirov epsilon-entropy of signal classes, optimal compression of signal classes

5. Uniform laws of large numbers: Rademacher complexity, Vapnik-Chervonenkis dimension, classes with polynomial discrimination
SkriptDetailed lecture notes will be provided at the beginning of the semester.
Voraussetzungen / BesonderesThis course is aimed at students with a background in basic linear algebra, analysis, statistics, and probability.

We encourage students who are interested in mathematical data science to take both this course and "401-4944-20L Mathematics of Data Science" by Prof. A. Bandeira. The two courses are designed to be complementary.

H. Bölcskei and A. Bandeira
227-0391-00LMedical Image Analysis
Basic knowledge of computer vision would be helpful.
W3 KP2GE. Konukoglu, M. A. Reyes Aguirre
KurzbeschreibungIt is the objective of this lecture to introduce the basic concepts used
in Medical Image Analysis. In particular the lecture focuses on shape
representation schemes, segmentation techniques, machine learning based predictive models and various image registration methods commonly used in Medical Image Analysis applications.
LernzielThis lecture aims to give an overview of the basic concepts of Medical Image Analysis and its application areas.
Voraussetzungen / BesonderesPrerequisites:
Basic concepts of mathematical analysis and linear algebra.

Preferred:
Basic knowledge of computer vision and machine learning would be helpful.

The course will be held in English.
  •  Seite  1  von  1