An essential requirement for artificial systems is the ability to deal with uncertainties. This ability is particularly important in intelligent and autonomous systems in which uncertainties arise, e.g. with regard to perception (What did I see? What didn't I see?), knowledge (How accurate, complete or up-to-date is my knowledge?), reasoning (How valid is my inference?) or actions (How good is my decision? Did I achieve everything?). In this lecture, techniques of reasoning and decision making under incomplete and uncertain knowledge are taught (graphical probabilistic model, Bayes/Markov networks, Markov decision processes, machine learning), which are used today in artificial intelligence and robotics to construct intelligent autonomous agents. In addition to the mathematical basics, the algorithms are also taught in the lecture. In the accompanying exercises, this is practically deepened in the form of small projects in Python.
(Siehe Eintrag zur Vorlesung)
Rhythmus | Tag | Uhrzeit | Format / Ort | Zeitraum | |
---|---|---|---|---|---|
14-täglich | Mi | 14-16 | CITEC 1.204 | 07.10.2024-31.01.2025 |
Die verbindlichen Modulbeschreibungen enthalten weitere Informationen, auch zu den "Leistungen" und ihren Anforderungen. Sind mehrere "Leistungsformen" möglich, entscheiden die jeweiligen Lehrenden darüber.
Studiengang/-angebot | Gültigkeit | Variante | Untergliederung | Status | Sem. | LP | |
---|---|---|---|---|---|---|---|
Studieren ab 50 |
Zu dieser Veranstaltung existiert ein Lernraum im E-Learning System. Lehrende können dort Materialien zu dieser Lehrveranstaltung bereitstellen: