I work on probabilistic machine learning, meaning probabilistic modelling and Bayesian inference, applied to difficult problems that are interesting and societally important. At the moment I work on the inter-related topics of analysis of multiple data sources, human-in-the-loop machine learning, simulator-based inference (likelihood-free inference with ABC), and privacy-preserving learning. I have had the chance to collaborate with amazing people in interdisciplinary research projects on applications in biology and medicine, brain signal analysis and user interaction (see list of publications), and in the Aalto Probabilistic Machine Learning Group which I lead with Prof. Aki Vehtari, and the Finnish Center of Excellence in Computational Inference Research which I lead until end of 2017.
To further boost the already strong artificial intelligence research and its impact, we are setting up a new Finnish Artificial Intelligence Center FCAI, which I will lead 2018-. It is a partnership of Aalto University, University of Helsinki, and a number of company members, networking further to key international and national partners. We aim to solve three bottleneck questions in AI research: data scarcity, dependability of AI, and ability of AI to understand its users (more details here). The research will be done with company partners, including new startups and spin-offs, which will take the results directly to use. We will also pay special attention to AI education.
Some recent papers (Full list on my research group's pages):
Human-in-the-loop machine learning, human-computer interaction:
Multiple data sources:
Simulator-based inference / likelihood-free inference:
Privacy-preserving machine learning: