Inhalt

[ 675MLDAMSTU13 ] UE (*)Machine Learning: Supervised Techniques

Versionsauswahl
Es ist eine neuere Version 2015W dieser LV im Curriculum Bachelorstudium Bioinformatics 2015W vorhanden.
(*) Leider ist diese Information in Deutsch nicht verfügbar.
Workload Ausbildungslevel Studienfachbereich VerantwortlicheR Semesterstunden Anbietende Uni
1,5 ECTS B2 - Bachelor 2. Jahr Informatik Ulrich Bodenhofer 1 SSt Johannes Kepler Universität Linz
Detailinformationen
Quellcurriculum Bachelorstudium Bioinformatics 2013W
Ziele (*) This practical course complements the lecture "Machine Learning: Supervised Techniques" and aims at practicing the concepts and methods acquired in the lecture.
Lehrinhalte (*)
  • Basics of classification and regression
  • Evaluation of machine learning results (confusion matrices, ROC)
  • Under- and overfitting / bias and variance
  • Cross-validation and hyperparameter selection
  • Logistic regression
  • Support vector machines and kernels
  • Neural networks and deep networks
  • Time series (sequence) analysis
  • Bagging and boosting
  • Feature selection and feature construction
Beurteilungskriterien (*)Marking is based on homework
Lehrmethoden (*)Students are given assignments in 1-2 week intervals. Homework must be handed in. 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? Nein
Äquivalenzen (*)in collaboration with 875BIN2MUTU13: UE Machine Learning: Unsupervised Techniques (1,5 ECTS) equivalent to
875BIN2TMLU12: UE Theoretical Bioinformatics and Machine Learning (3 ECTS) -or- BIMPHUEBIN2: UE Bioinformatik II: Theoretische Bioinformatik und Maschinelles Lernen (3 ECTS)
Präsenzlehrveranstaltung
Teilungsziffer 35
Zuteilungsverfahren Direktzuteilung