Foundations for Machine Learning

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche

Foundations for Machine Learning

Lehrveranstaltung mit SWS 2/0/0 (Vorlesung/Übung/Praktikum) in SS 2019

Dozent

  • Yohanes Stefanus

Umfang (SWS)

  • 2/0/0

Module

Leistungskontrolle

  • Klausur
  • Mündliche Prüfung

Content

The topic of this course is mathematical foundations for Machine Learning. We define the term "machine learning" to mean the automated detection of meaningful patterns in data. Nowadays machine learning based technologies are ubiquitous: digital economic systems, web search engines, anti-spam software, credit/insurance fraud detection software, accident prevention systems, bioinformatics, etc. This course provides a theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms, such as algorithms appropriate for big data learning. We will start with Valiant's PAC (Probably Approximately Correct) learning model, the ERM (Empirical Risk Minimization) learning rule, the No-Free-Lunch Theorem, and the VC (Vapnik-Chervonenkis) dimension. The course will end with deep learning.


Schedule

Please check this website regularly as there might be changes!

The lecture will take place from 17th June till 5th July 2019 on the following days:

  • Monday, 17th June from 14:50 - 16:20 pm at APB 2026 (room might change depending on number of students)
  • Tuesday, 18th June from 14:50 - 16:20 pm at SCH/A216/H (Schumann-Bau)
  • Friday, 21st June from 09:20 - 10:50 am at APB E046 (Andreas-Pfitzmann-Bau)


  • Monday, 24th June from 14:50 - 16:20 pm at SCH/A215/H (Schumann-Bau)
  • Tuesday, 25th June from 14:50 - 16:20 pm at SCH/A216/H (Schumann-Bau)
  • Wednesday, 26th June from 14:50 - 16:20 pm at SCH/A216/H (Schumann-Bau)
  • Thursday, 27th June from 16:40 - 18:10 pm at HSZ/105/U (Hörsaalzentrum)
  • Friday, 28th June from 09:20 - 10:50 am at APB E046 (Andreas-Pfitzmann-Bau)


  • Monday, 1st July from 14:50 - 16:20 pm at SCH/A215/H (Schumann-Bau)
  • Tuesday, 2nd July from 14:50 - 16:20 pm at SCH/A216/H (Schumann-Bau)
  • Wednesday, 3rd July from 14:50 - 16:20 pm at SCH/A216/H (Schumann-Bau)
  • Thursday, 4th July from 16:40 - 18:10 pm at HSZ/105/U (Hörsaalzentrum)
  • Friday, 5th July from 09:20 - 10:50 am at HSZ/101/U (Hörsaalzentrum)


The written examination will be on 8th July, 2019 from 14:50 - 16:20 pm at HÜL/S186/H (Hülsse-Bau)


Registration

Registration for the course by 30th May, 2019

* CL-Students: please send an Email to cl@mailbox.tu-dresden.de

* CMS-Students: Please register via SELMA-portal and consider the valid deadline

* Other Students: Please register via jexam https://jexam.inf.tu-dresden.de/de.jexam.web.v4.5/spring/welcome


Lecture Slides


Prerequisites

  • Probability Theory
  • Linear Algebra
  • Algorithm Design & Analysis
  • Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014.

An electronic version of the book is accessable via TU network here

  • Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press, 2016.
An electronic version of the book is accessable via TU network here