Project “Machine Teaching for Explainable AI" funded by Research Council

We congratulate our professor Jan Arne Telle who has obtained funding for the project “Machine Teaching for Explainable AI”.  

The Research Council of Norway has decided to support the project with 10 million NOK through their Enabling technologies program. The project involves the companies Equinor and BKK AS and also includes Pekka Parviainen in our machine learning group.

The project aims to develop methods to explain decisions based on use of Artificial Intelligence (AI) methods making the reasoning performed within the AI method understandable for a human. The companies involved are increasingly using AI methods in their operations and are eager to engage in the project since they see a need to better integrate AI methods in their operations.

As stated in the project proposal:

"The last decade has witnessed an explosive rise in the use of decision systems built on modern AI techniques that are often opaque, such as deep learning. These black-box systems, based on large amountsof data, are a key tool in making important decisions for both individuals, companies and society at large. It is of greatest importance that the users can evaluate and trust these decisions. The field of explainable artificial intelligence (XAI) addresses this issue, to give human users a better understanding of the behavior of complex AI systems."