Inhalt

[ 921PECOMLPU20 ] UE (*)Machine Learning and Pattern Classification

Versionsauswahl
(*) Leider ist diese Information in Deutsch nicht verfügbar.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
1,5 ECTS M1 - Master 1. Jahr Informatik Gerhard Widmer 1 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Masterstudium Computer Science 2021W
Ziele (*)Students will learn, in a practical, exploratory way, what it means to apply standard machine learning algorithms to real-world problems, by experimenting with learning and classification algorithms in a non-trivial application task. This will give them a critical understanding of the complexity of real-world learning, the methodology of systematic experimentation, critical evaluation of results, and possible pitfalls.
Lehrinhalte (*)Using public machine learning toolboxes, students will go through all the stages of a pattern classification project of real-world complexity, from annotation, feature definition and extraction to the training of various classifiers and systematic experimentation.
Beurteilungskriterien (*)Several written project reports throughout the course of the project.
Lehrmethoden (*)Independen work by students / student groups. Joint discussion of practical work. Presentations by lecturer and selected students or student groups.
Abhaltungssprache Englisch
Literatur (*)Will be provided if needed.
Lehrinhalte wechselnd? Nein
Äquivalenzen (*)in collaboration with 921PECOMLPV20: VL Machine Learning and Pattern Classification (3 ECTS) equivalent to
921PECOMLPK13: KV Machine Learning and Pattern Classification (4.5 ECTS)
Präsenzlehrveranstaltung
Teilungsziffer 35
Zuteilungsverfahren Direktzuteilung