Inhalt

[ INMAWUETCML ] UE Theoretical Concepts of Machine Learning

Versionsauswahl
Es ist eine neuere Version 2013W dieser LV im Curriculum Masterstudium Bioinformatics (auslaufend) 2019W vorhanden.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
1,5 ECTS M2 - Master 2. Jahr Informatik Ulrich Bodenhofer 1 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Masterstudium Informatik (auslaufend) 2012W
Ziele This practical course complements the lecture "Theoretical Concepts of Machine Learning" and aims at practicing the concepts and methods acquired in the lecture.
Lehrinhalte
  • Generalization error
  • Bias-variance decomposition
  • Error models
  • Model comparisons
  • Estimation theory
  • Statistical learning theory
  • Worst-case and average bounds on the generalization error
  • Structural risk minimization
  • Bayes framework
  • Evidence framework for hyperparameter optimization
  • Optimization techniques
  • Theory of kernel methods
Beurteilungskriterien Marking is based on homework
Lehrmethoden Students are given assignments in 1-2 week intervals. Homework must be handed. Results are to be presented and discussed in the course.
Abhaltungssprache Englisch
Literatur Assignments and homework submissions are managed via JKU Moodle. Where necessary, complimentary course material is provided for download.
Lehrinhalte wechselnd? Ja
Präsenzlehrveranstaltung
Teilungsziffer 35
Zuteilungsverfahren Direktzuteilung