Thema4698
Aus Aifbportal
Interactive Evolutionary Multiobjective Optimization
Informationen zur Arbeit
Abschlussarbeitstyp: Master
Betreuer: Jacqueline Höllig
Forschungsgruppe: Web Science
Partner: FZI
Archivierungsnummer: 4698
Abschlussarbeitsstatus: Offen
Beginn:
01. Dezember 2020
Abgabe: unbekannt
Weitere Informationen
Inhaltsverzeichnis
Thema
Investigating and Developing approaches to generate realistic and human-interpretable image counterfactuals by using Multiobjective Optimization.
Aufgaben
- In-depth literature review about Interactive Multiobjective Optimization and Evolutionary Multi-Objective Optimization
- Development of an interactive evolutionary Multobjective approach for image counterfactuals
- Experimental comparison of state-of-the-art image counterfactuals with the newly developed approach
Wir bieten
- Continuous and thorough mentoring of the student
- A highly motivated and fun team
- Constructive teamwork
Wir erwarten
- Basic knowledge in python programming and/or machine learning
- Ability to plan and work independently
- Very good knowledge of German or English
- High level of motivation and enthusiasm
Bewerbung
We are looking forward to your application to Jacqueline Höllig (hoellig∂fzi de). Please provide us with the following information:
- Transcript of Records
- CV