I’m a senior researcher at Nokia Technologies working on deep neural network compression and explainable AI. Prior to that I was a postdoctoral researcher in the Multi-Source Probabilistic Inference group at University of Helsinki working with Professor Arto Klami.

I completed my PhD in the Probabilistic Machine Leanring group under supervision of Professor Samuel Kaski in 2019. My thesis research lied in the space of human-in-the-loop machine learning with focus on knowledge elicitation, probabilistic modeling, and active learning. You can download my thesis here. After finishing my PhD and before starting the postdoctoral position, I had the opportunity to work with some amazing people at Sony AI in Tokyo, as a visiting researcher.

My main research interests include:

• Neural network compression: reducing the size of deep neural network models while maitaining their predictive performance as much as possible to ease their usage in decentralized environment.
• Machine learning Interpretability: making machine learning models understandable for human decision makers.
• Human-in-the-loop machine learning: combining human and machine intelligence to create more powerful models.