Human-Learner-Interaction

Termine

TagZeitRhythmusZeitraumRaumLehrpersonBemerkungMax. Teilnehmer/-innen
Vorlesung (V) - Termine:
Do. 09:00 bis 19:00 Einzeltermin am 05.04.2018 G22A-004 (20 Plätze)    
Fr. 09:00 bis 19:00 Einzeltermin am 06.04.2018 G22A-004 (20 Plätze)    
Di. 17:00 bis 19:00 wöchentlich 10.04.2018 bis
19.06.2018
  Krempl Lehrpreisträger/-in

Consultation Time (individual appointments per group will be scheduled accordingly)

Seminar/Übung (S/Ü) - Termine:
Di.15:00 bis 17:00 s.t.wöchentlich  Krempl Lehrpreisträger/-in

Consultation time (on individual appointment)

Übersicht (from LSF)

Lerninhalte

Aims & Competences:

  • Students should understand selected current research challenges in the field of machine learning/data science, in particular in the area of active, semi-supervised and transfer learning. They should be able to apply and analyse novel methods that will be discussed and developed within the course.

  • Students should gain practical expericience in project management, as wel as in (scientific) programming and writing.

Kurzkommentar<p style="margin-bottom: 0cm; line-height: 100%;">This <strong>block course (Deutsch: geblockte Lehrveranstaltung)</strong> is a combined lecture, seminar and project. Following a block lecture at the beginning of the term, the course is centred around work in small groups on projects that address a topic of <strong>current research in machine learning/data science</strong>. In 2018, the projects will be within the topic of <strong>active transfer learning</strong>, further details will be announced in the first lectures. Knowledge of fundamental concepts in data mining/machine learning is expected as prerequisite.</p><p><strong> Mandatory course registration: see "enrollment/Belegfunktion" for the accompanying Seminar/Exercise in LSF. The binding registration and topic/team assignment will be done right after the c<strong>ompulsatory exercises (tests) at the end of the lecture <strong><strong>block.</strong></strong></strong><br /></strong></p>
Literatur

Selected research-oriented topics, for example from:

Active Learning:

Burr Settles. Active Learning. Morgan and Claypool Publishers, 2012.

Semi-Supervised Learning:

Steve Abney. Semisupervised Learning for Computational Linguistics. Chapman & Hall/CRC Computer Science & Data Analysis Series, 2007.

Reinforcement Learning

Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.

Recommender Systems:

Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul B. Kantor (Hrg.). Recommender Systems Handbook. Springer 2010.

Voraussetzungen

Basic knowledge of data mining oder machine learning is highly recommended.

Mandatory course registration: see "enrollment/Belegfunktion" for the accompanying Seminar/Exercise in LSF.

Zielgruppe
  • B-CV: WPF FIN-SMK

  • B-CV: WPF INF

  • B-INF: WPF FIN-SMK

  • B-INF: WPF INF

  • B-INGINF: WPF FIN-SMK

  • B-INGINF: WPF INF

  • B-WIF: WPF FIN-SMK

  • B-WIF: WPF INF

  • M-DKE: WPF Methods 1 / Fundamentals

  • M-DigiEng: WPF Human Factors

 

Course Material

 

Last Modification: 26.03.2018 - Contact Person: