More certainty for deep learning
Deep learning, machine learning and artificial intelligence offer significant opportunities to solve the challenges of different disciplines and make our lives easier in many ways.
Lassi Meronen develops deep learning models that know how to estimate their own uncertainty computationally.
"There is still a lot to be developed in technology modeling, especially in assessing uncertainty. Deep learning models may fail, for example, in situations where the model encounters something new that it has not seen before. Saab offers many fascinating, real-life application challenges that take my research forward,” says Lassi Meronen.
He discusses the topic in a video with Assistant Professor Arno Solin: