Inhalt

[ 536MLPEMUTU19 ] UE Machine Learning: Unsupervised Techniques

Versionsauswahl
Es ist eine neuere Version 2023W dieser LV im Curriculum Master's programme Mechatronics 2023W vorhanden.
Workload Education level Study areas Responsible person Hours per week Coordinating university
1,5 ECTS B2 - Bachelor's programme 2. year Computer Science Sepp Hochreiter 1 hpw Johannes Kepler University Linz
Detailed information
Original study plan Bachelor's programme Artificial Intelligence 2019W
Objectives This practical course complements the lecture "Machine Learning: Unsupervised Techniques" and aims at practicing the concepts and methods acquired in the lecture.
Subject
  • Error models
  • Information bottleneck
  • Maximum likelihood and the expectation maximization algorithm
  • Maximum entropy methods
  • Basic clustering methods, hierarchical clustering, and affinity propagation
  • Mixture models
  • Principal component analysis, independent component analysis, and other projection methods
  • Factor analysis
  • Matrix factorization
  • Auto-associator networks and attractor networks
  • Boltzmann and Helmholtz machines
  • Hidden Markov models
  • Belief networks
  • Factor graphs
Criteria for evaluation Marking is based on homework
Methods Students are given assignments in 1-2 week intervals. Homework must be handed in. Results are to be presented and discussed in the course.
Language English
Study material Assignments and homework submissions are managed via JKU Moodle. Where necessary, complimentary course material is provided for download.
Changing subject? No
Corresponding lecture 875BIMLMUTU16: UE Machine Learning: Unsupervised Techniques (1,5 ECTS)
Earlier variants They also cover the requirements of the curriculum (from - to)
875BIMLMUTU16: UE Machine Learning: Unsupervised Techniques (2016W-2019S)
875BIN2MUTU13: UE Machine Learning: Unsupervised Techniques (2013W-2016S)
On-site course
Maximum number of participants 35
Assignment procedure Direct assignment