Universität Wien FIND

Due to the COVID-19 pandemic, changes to courses and exams may be necessary at short notice (e.g. cancellation of on-site teaching and conversion to online exams). Register for courses/exams via u:space, find out about the current status on u:find and on the moodle learning platform.

Further information about on-site teaching can be found at https://studieren.univie.ac.at/en/info.

052414 VU Concepts and Models of Knowledge Engineering (2018W)

Continuous assessment of course work

Summary

1 Karagiannis , Moodle
2 Karagiannis , Moodle

Registration/Deregistration

Registration information is available for each group.

Groups

Group 1

max. 25 participants
Language: English
LMS: Moodle

Lecturers

Classes (iCal) - next class is marked with N

Wednesday 03.10. 08:00 - 09:30 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 03.10. 15:00 - 16:30 Seminarraum 7, Währinger Straße 29 1.OG
Wednesday 21.11. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 22.11. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 28.11. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 29.11. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 05.12. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 06.12. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Monday 10.12. 08:00 - 09:30 Hörsaal 1, Währinger Straße 29 1.UG
Wednesday 12.12. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 09.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 10.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 16.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 17.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 23.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 24.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Monday 28.01. 15:00 - 16:30 Hörsaal 14 Oskar-Morgenstern-Platz 1 2.Stock

Group 2

max. 25 participants
Language: English
LMS: Moodle

Lecturers

Classes (iCal) - next class is marked with N

Wednesday 03.10. 08:00 - 09:30 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 03.10. 15:00 - 16:30 Seminarraum 7, Währinger Straße 29 1.OG
Wednesday 21.11. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 22.11. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 28.11. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 29.11. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 05.12. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 06.12. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Monday 10.12. 08:00 - 09:30 Hörsaal 1, Währinger Straße 29 1.UG
Wednesday 12.12. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 09.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 10.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 16.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 17.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Wednesday 23.01. 13:15 - 14:45 Hörsaal 3, Währinger Straße 29 3.OG
Thursday 24.01. 09:45 - 11:15 Hörsaal 3, Währinger Straße 29 3.OG
Monday 28.01. 15:00 - 16:30 Hörsaal 14 Oskar-Morgenstern-Platz 1 2.Stock

Information

Aims, contents and method of the course

In this lecture, the goal is to gain expertise on the state of the art in knowledge engineering. Therefore, students explore the relevant theory and reinforce their knowledge in exercises.

Assessment and permitted materials

Two exams have to be written, one in the middle and one at the end of the semester. The exams will contain theory questions and applied problems, based on the lectures, a script with lecture content, and exercises. During the test, no unauthorized materials are allowed and all electronic devices have to be turned off.

In detail, the grade is constituted by:
* 1st exam 40%
* 2nd exam 40%
* Exercises 20%

Missing class more than three times results in a negative grade.

Minimum requirements and assessment criteria

For a positive evaluation of the course, more or equal to 50% of requirements have to be fulfilled. The grading scale is defined as follows: >50% - 62,5%: Genügend; >62,5% - 75%: Befriedigend; >75% - 87,5%: Gut; >87,5%: Sehr Gut

Examination topics

Neural Networks I
Machine Learning
Neural Networks II
Evolutionary Computation
Bayesian Scheme
Hidden Markov Models
Agent Systems
Constraint Satisfaction
Semantic Web

Reading list

Script with lecture content
Moodle course

Dimitris Karagiannis, Rainer Telesko: Wissensmanagement: Konzepte der künstlichen Intelligenz und des Softcomputing
Stuart J. Russell, Peter Norvig: Artificial Intelligence - A Modern Approach

Association in the course directory

Module: WI2 KE

Last modified: Mo 07.09.2020 15:30