How Can Reliability of Artificial Intelligence Be Ensured?
MCML Authors
Gitta Kutyniok
Prof. Dr.
Principal Investigator
Abstract
Gitta Kutyniok
Prof. Dr.
Principal Investigator
Abstract
Column Editor’s Note: Artificial intelligence (AI) is having a profound impact across many areas of science and society. However, there remain important gaps in our understanding of the deep neural networks that underpin these developments, and in many cases AI models lack robustness and reliability. In this Diving into Data column, Professor Kutyniok explores these issues from a mathematical perspective, highlighting open theoretical questions that will need to be resolved in order to develop AIs that are truly reliable, generalizable, and trustworthy.
BibTeXKey: Kut25