392101 Cognitive Computing: Reasoning and Decision-Making Under Uncertainty (V) (WiSe 2024/2025)

Contents, comment

Eine wesentliche Anforderung an künstliche Systeme ist es, mit Unsicherheiten umgehen zu können. Ganz besonders zentral ist diese Fähigkeit in intelligenten und autonomen Systemen, in denen Unsicherheiten z.B. bzgl. der Wahrnehmung (Was habe ich gesehen? Was nicht?), des Wissens (Wie zutreffend, vollständig oder aktuell ist mein Wissen?), des Schließens (Wie gültig ist meine Inferenz?) oder der Aktionen (Wie gut ist meine Entscheidung?Hat ich alles erreicht?) entstehen. In dieser Vorlesung werden Techniken des Schließens und Entscheidens unter unvollständigem und unsicherem Wissen vermittelt (graphische probabilistische Modell, Bayes-/Markov-Netze, Markov-Entscheidungsprozesse, maschinelles Lernen), mit denen in der Künstlichen Intelligenz und Robotik heutzutage intelligente autonome Agenten konstruiert werden. Neben den mathematischen Grundlagen werden auch die Algorithmen erarbeitet. Die Vorlesung wird von praktischen Programmierübungen in Form kleiner Projekte in Python begleitet.

Grober Aufbau der Vorlesung:
1. Einführung und mathematische Grundlagen (Wahrscheinlichkeits-, Graphentheorie)
2. Probablilistische graphische Modelle
3. Exakte und approximative Inferenzverfahren (Sampling)
4. Entscheidungsbäume und -netze, Markov-Entscheidungsprozesse
5. Lernen von probabilistischen Modellen, Reinforcement Learning

Bibliography

Darwiche (2000). Modeling and Reasoning with Bayesian Networks. Cambridge Univ. Press.
Koller & Friedman, Probabilistic Graphical Models, MIT Press
Barber, Bayesian Reasoning and Machine Learning, Cambridge Univ. Press
J. Pearl (2009) Causality: Models, Reasoning and Inference. 2nd edition, Cambridge Univ. Press.
Russel & Norvig (2002). Artificial Intelligence: A modern approach. 2nd edition, Prentice Hall.

Teaching staff

Dates ( Calendar view )

Frequency Weekday Time Format / Place Period  
weekly Fr 10-12 Unpublished 07.10.2024-31.01.2025

Subject assignments

Module Course Requirements  
39-Inf-EGMI Ergänzungsmodul Informatik vertiefende Informatikvorlesung 2.1 Ungraded examination
Student information
39-Inf-KR Cognitive Computing / Kognitives Rechnen Kognitives Rechnen Ungraded examination
Graded examination
Student information
39-Inf-WP-KI-x Künstliche Intelligenz (Schwerpunkt) Einführende Veranstaltung Seminar o. Vorlesung Student information
- Graded examination Student information
39-M-Inf-AI-adv-foc Advanced Artificial Intelligence (focus) Advanced Artificial Intelligence (focus): Vorlesung Student information
39-M-Inf-AI-app Applied Artificial Intelligence Applied Artificial Intelligence: Vorlesung Student information
- Graded examination Student information
39-M-Inf-AI-bas Basics of Artificial Intelligence Basics of Artificial Intelligence: Vorlesung Student information
- Ungraded examination Student information
39-M-Inf-VKI Vertiefung Künstliche Intelligenz Spezielle Themen der Künstlichen Intelligenz Ungraded examination
Graded examination
Student information
39-M-Inf-VKIa Vertiefung Künstliche Intelligenz (5 LP) Spezielle Themen der Künstlichen Intelligenz Graded examination
Student information

The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.

Degree programme/academic programme Validity Variant Subdivision Status Semester LP  
Studieren ab 50    

No more requirements
No E-Learning Space
Registered number: 8
This is the number of students having stored the course in their timetable. In brackets, you see the number of users registered via guest accounts.
Address:
WS2024_392101@ekvv.uni-bielefeld.de
This address can be used by teaching staff, their secretary's offices as well as the individuals in charge of course data maintenance to send emails to the course participants. IMPORTANT: All sent emails must be activated. Wait for the activation email and follow the instructions given there.
If the reference number is used for several courses in the course of the semester, use the following alternative address to reach the participants of exactly this: VST_475008168@ekvv.uni-bielefeld.de
Coverage:
8 Students to be reached directly via email
Notes:
Additional notes on the electronic mailing lists
Last update basic details/teaching staff:
Tuesday, June 25, 2024 
Last update times:
Tuesday, May 28, 2024 
Last update rooms:
Tuesday, May 28, 2024 
Type(s) / SWS (hours per week per semester)
V / 2
Language
This lecture is taught in english
Department
Faculty of Technology
Questions or corrections?
Questions or correction requests for this course?
Planning support
Clashing dates for this course
Links to this course
If you want to set links to this course page, please use one of the following links. Do not use the link shown in your browser!
The following link includes the course ID and is always unique:
https://ekvv.uni-bielefeld.de/kvv_publ/publ/vd?id=475008168
Send page to mobile
Click to open QR code
Scan QR code: Enlarge QR code
ID
475008168