Insights into artificial intelligence: Understanding and explaining decisions
Artificial intelligence powered methods are currently finding their way into almost every sphere of public life, where they often replace long-established traditional methods with great success. We are also seeing artificial intelligence exert a similarly strong influence in many scientific fields, such as astronomy, medicine and even the humanities. Despite this impressive rise in the technology’s impact, there is still a lack of understanding around the processes by which artificial intelligence actually makes decisions. Moreover, undesirable effects such as unforeseen wrong decisions remain a problem.
In her lecture, Gitta Kutyniok, Professor of Mathematics at LMU, starts by giving an introduction to artificial intelligence and explaining why these new methodologies are so extremely successful. She then goes into the extent to which artificial intelligence decisions are currently understood and can be explained to users. To finish, Gitta Kutyniok makes some suggestions as to how transparency, explainability and security around artificial intelligence can be achieved from a mathematical perspective.
Professor Gitta Kutyniok holds the Chair for Mathematical Foundations of Artificial Intelligence in the Faculty of Mathematics, Computer Science and Statistics, which is one of the AI professorships funded under the State of Bavaria’s High-Tech Agenda.