UnivIS
Informationssystem der Otto-Friedrich-Universität Bamberg © Config eG 
Zur Titelseite der Universität Bamberg
  Sammlung/Stundenplan Home  |  Anmelden  |  Kontakt  |  Hilfe 
Suche:      Semester:   
 
 Darstellung
 
Druckansicht

 
 
 Außerdem im UnivIS
 
Vorlesungsverzeichnis

 
 
Veranstaltungskalender

 
 

  xAI-Proj-M: Masterprojekt Erklärbares Maschinelles Lernen

Dozentinnen/Dozenten
Francesco Di Salvo, Prof. Dr. Christian Ledig

Angaben
Übung
Rein Präsenz
4,00 SWS, Unterrichtssprache Deutsch
Zeit und Ort: Di 14:00 - 18:00, WE5/04.003; Bemerkung zu Zeit und Ort: Initial Meeting on October 17th - 17/10/23- (Q&A and preliminary overview- not mandatory), Kick-off: 24/10/23 (mandatory for participants)

Englischsprachige Informationen:
Title:
xAI-Proj-M: Masterproject Machine Learning

Credits: 6

Prerequisites
Degree Program: M.Sc. AI, M.Sc. WI, M.Sc. ISoSySc, M.Sc. CitH
Requirements: Successfully passed the exam xAI-DL-M, xAI-MML-M, KogSys-ML-M or AI-KI-B (Introduction to AI).
Beneficiaries: Knowledge in programming (Python), Hands-on knowledge in machine learning and deep learning, scientific writing, LaTeX.
Registration: Email with name, matriculation number, degree program, and completed ML-related modules to francesco.di-salvo@uni-bamberg.de

Contents
Machine learning has become increasingly popular in recent years, with its applications expanding to healthcare, finance, energy, and many other sectors. However, there are still a number of critical challenges that need to be addressed before these models can be safely and robustly adopted in widespread use.
The goal of this project is to develop robust machine learning algorithms that can perform reliably in challenging real-world scenarios. Working in teams of 4, students will have the chance to explore one of the following topics: explainability, robustness toward image corruptions, robustness toward out-of-distribution data, model calibration, model efficiency, and data efficiency. After understanding the challenges and limitations of the chosen topic through the assigned paper(s), under the guidance of the instructor, students will formulate, investigate, and validate their own research questions.
Finally, the students will present their results to their peers and submit a technical report describing the ideas, methods, and the results.

Zusätzliche Informationen
Erwartete Teilnehmerzahl: 20

Institution: Lehrstuhl für Erklärbares Maschinelles Lernen

Hinweis für Web-Redakteure:
Wenn Sie auf Ihren Webseiten einen Link zu dieser Lehrveranstaltung setzen möchten, verwenden Sie bitte einen der folgenden Links:

Link zur eigenständigen Verwendung

Link zur Verwendung in Typo3

UnivIS ist ein Produkt der Config eG, Buckenhof