Foundations for Maschine Learning

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

Foundations for Maschine Learning

Lehrveranstaltung mit SWS 4/2/0 (Vorlesung/Übung/Praktikum) in SS 2018

Dozent

  • Yohanes Stefanus

Umfang (SWS)

  • 4/2/0

Module

Leistungskontrolle

  • Referat


  • The lecture will take place from 11th June till 20th July 2018.

2 Credits can be achieved.*


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.
  • Shai Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press, 2014.
  • Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. MIT Press, 2016.