Differences between revisions 5 and 6
Revision 5 as of 2018-04-13 14:30:21
Size: 2294
Comment:
Revision 6 as of 2018-04-16 11:59:03
Size: 2294
Comment:
Deletions are marked like this. Additions are marked like this.
Line 8: Line 8:
||'''Lecture'''|| Mondays 14:00-16:00 in room H 2032 ||
||'''Exercise session'''|| Mondays 16:00-18:00 in room H 2032 ||
||'''Lecture'''|| Mondays 14:15-16:00 in room H 2032 ||
||'''Exercise session'''|| Mondays 16:15-18:00 in room H 2032 ||

Maschinelles Lernen - Theorie und Anwendung

General Information

Maschinelles Lernen - Theorie und Anwendung is a 9 LP (9 ECTS) credits module.

Lecture period

16.04.2018-21.07.2018

Lecture

Mondays 14:15-16:00 in room H 2032

Exercise session

Mondays 16:15-18:00 in room H 2032

Language

English

Trainers

Prof. Dr. Klaus-Robert Müller (Responsible)

Gregoire Montavon

Contact

gregoire.montavon@tu-berlin.de

ISIS

https://isis.tu-berlin.de/course/view.php?id=12858

Frequently asked questions (FAQ):

How many credits for this course? 6 ECTS if taken as a standalone course. 9 ECTS if taking the whole module (i.e. including an optional course, see below for a list).

Is it possible to take this course without having taken ML1? Yes, ML1 is not a formal prerequisite. However, methods learned in ML1 will be assumed to be known, and extra work might therefore be needed during the first few weeks.

I am from a different university, can I take this course? If you are not a student at TU and want to earn credit, you have to solicit ''Nebenhörerschaft'': (1) Print out the forms concerning Nebenhörerschaft you find on that page. (2) Pass by at my office (see above) to have them signed, or bring your forms during the first lecture. (3) In addition, the dean of faculty IV has to sign. (4) Register at the the Campus Center. You will receive a TUBIT account (see below).

Topics

  • Embeddings
  • Stationary Subspace Analysis
  • Independent Component Analysis
  • Canonical Correlation Analysis
  • Kernel methods for structured data
  • Neural networks for structured data
  • Unsupervised neural networks
  • Structured output learning
  • One-class SVMs
  • Bioinformatics

List of optional courses

IDA Wiki: Main/SS18_ML2 (last edited 2018-04-16 11:59:03 by GrégoireMontavon)