Zurück
| Semester | Frühjahrsemester 2024 |
| Angebotsmuster | Jedes Frühjahrsem. |
| Dozierende | Volker Roth (volker.roth@unibas.ch, BeurteilerIn) |
| Inhalt | In this seminar we will discuss together the main concepts of reasoning under uncertainty. We will discuss questions such as: How is uncertainty represented and quantified? How can we use probability theory to reason under uncertainty? How can we make good decisions if we have uncertain information? We will also discuss different methods for learning from examples and look at strategies to learn when no examples, but only an assessment of the outcome of a situation is available (reinforcement learning). Finally, we will see these methods in application in the context of natural language processing. Each participant will be assigned a topic, which he/she will summarize and present during the seminar. The topic is studied individually by the student, with the help of a tutor. |
| Lernziele | At the end of the course, students should have a good overview of different formalisms, methods and strategies to reason about uncertainty. Participants should also have learned to study, summarize and present scientific literature to a peer group in an understandable and instructive way. |
| Literatur | Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach. |
| Weblink | Webseite Fachbereich Informatik |
| Teilnahmebedingungen | Open to Master and PhD students with basic knowledge in probability theory and statistics, linear algebra and some first introduction to learning, as for example taught in the course pattern recognition. The number of participants is limited to 20 students. A binding seminar registration can be made by sending an email to Volker Roth (volker.roth@unibas.ch) on a first-come-first-served basis. To confirm the registration, each student has to participate in the first lecture. If a participation is not possible due to urgent cases, please send an email to volker.roth@unibas.ch. |
| Anmeldung zur Lehrveranstaltung | https://courses.cs.unibas.ch The number of participants is limited to 20 students. |
| Unterrichtssprache | Englisch |
| Einsatz digitaler Medien | Online-Angebot fakultativ |
| Intervall | Wochentag | Zeit | Raum |
|---|---|---|---|
| wöchentlich | Montag | 10.15-12.00 | Spiegelgasse 1, Seminarraum 00.003 |
| Datum | Zeit | Raum |
|---|---|---|
| Montag 04.03.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 11.03.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 18.03.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 25.03.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 01.04.2024 | 10.15-12.00 Uhr | Ostern |
| Montag 08.04.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 15.04.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 22.04.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 29.04.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 06.05.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 13.05.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Montag 20.05.2024 | 10.15-12.00 Uhr | Pfingstmontag |
| Montag 27.05.2024 | 10.15-12.00 Uhr | Spiegelgasse 1, Seminarraum 00.003 |
| Module |
Doktorat Informatik: Empfehlungen (Promotionsfach: Informatik) Modul: Applications of Distributed Systems (Masterstudium: Computer Science) Modul: Applications of Machine Intelligence (Masterstudium: Computer Science) Modul: Computer Science Project (Master Studienfach: Computer Science) Modul: Machine Learning Foundations (Masterstudium: Data Science) Modul: Methods of Machine Intelligence (Masterstudium: Computer Science) |
| Leistungsüberprüfung | Lehrveranst.-begleitend |
| Hinweise zur Leistungsüberprüfung | The final grade of the course is composed of the grade from 2 individual parts: - A presentation about one of the topics discussed in the course book - Preparation and presentation of a poster about a (broader) topic |
| An-/Abmeldung zur Leistungsüberprüfung | Anm.: Belegen Lehrveranstaltung; Abm.: stornieren |
| Wiederholungsprüfung | keine Wiederholungsprüfung |
| Skala | 1-6 0,5 |
| Wiederholtes Belegen | beliebig wiederholbar |
| Zuständige Fakultät | Philosophisch-Naturwissenschaftliche Fakultät, studiendekanat-philnat@unibas.ch |
| Anbietende Organisationseinheit | Fachbereich Informatik |