A new self-supervised machine learning approach captures word meaning with concise logical expressions. The logical expressions consist of contextual words like "black," "cup," and "hot" to define other words like "coffee," thus being human-understandable. This logical embedding performs competitively on several intrinsic and extrinsic benchmarks, matching pre-trained GLoVe embeddings on six downstream classification tasks.

PhD Research Fellow at the University of Agder develops a novel interpretable reinforcement learning paradigm.

A research fellow at UiA has developed an artificial intelligence programme to mitigate fake news.

UiA is the first university in Scandinavia to enter a research collaboration with CERN and the CMS experiment, as an associate member.