Teory and Algorithms of Machine Learning for Communication

Attention [COVID Requirements for participation: "3G" rule] https://www.berlin.de/corona/massnahmen/verordnung/


The lecture Theory and Algorithms of Machine Learning for Communication held by Prof. Dr.-Ing. Slawomir Stanczak will start this semester on Monday,  April, 25th 2022. The course takes as prsence lecture every Monday from 2pm to 4pm (c.t.) in the HFT-TA building room 131 . The last lecture will be on July,18th 2022.

A password for enrollment has been set for this course. Please request this by e-mail (sekretariat@netit.tu-berlin.de ) with the following information:

  • Study program
  • Matriculation number
  • Desired participation (online or in presence)

Theory and Algorithms of Machine Learning for Communication is part of the module Mathematics of Machine Learning. In order to complete the whole module with 6 Credit Points, the students must also cover the lecture Mathematical Introduction to Machine Learning which is offered every winter term by Dr. rer. nat. Igor Bjelakovic.

After completing both lectures the students will be tested in one oral exam or in two separated oral exams. Ask for an examination date and write an E-Mail to sekretariat@netit.tu-berlin.de . The registration for the module will be proceeded at the Examination Office (Prüfungsamt). You will receive a yellow sheet --> bring it to the exam (without sheet, no exam!)

Please note that you will only receive CP´s for the full completed module. Only for exchange students the following regulation applies:

Information for exchange students: it is possible to be examined only in one lecture of the module with 3CP. You do not need to register at the Examination Office, simply ask for an examination date via E-Mail to sekretariat@netit.tu-berlin.de. After passing the exam you receive a certificate for the International Office.

 

Terms of Use

The lecture notes of this course are exclusively for the personal use of the enrolled students. Any type of distribution, reproduction, disclosure, and non-personal usage is prohibited. 

Moreover, recording the lectures in any form (including audio and video), even partially and for private use, is strictly forbidden.

All data, especially personal and confidential data, must be protected by the student in such a way that unauthorized access and unauthorized access to the data and documents is effectively prevented. Data, information or documents may not be passed on to third parties nor may they be made available for inspection by third parties (e.g. on screen or on printouts). The student is responsible for compliance with this principle and for the possible consequences of non-compliance.

  • Datenschutzgrundverordnung (DSGVO) Link
  • Berliner Datenschutzgesetz Link
  • §§ 6, 6a Berliner Hochschulgesetz (BerlHG) Link
  • Berliner Informationsfreiheitsgesetz Link

 

 

Recommended literature:

P. Rigollet: Mathematics of Machine Learning, MIT Lecture Notes (online)

R. Vershynin: High-Dimensional Probability: An Introduction with Applications in Data Sciences (book in preparation, online)

S. Shalev-Schwartz and S. Ben-David: Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press 2014