I investigate the geometric science of information with applications ranging from machine learning to data science, visual computing, and artificial intelligence.
I deal with large high-dimensional, noisy, and heterogeneous dynamic datasets that are inherently non-Euclidean in nature.
To build advanced models and learning machines that capture both regularities and variations of datasets,
I develop geometric computational methods and toolboxes.
Since 2013, I co-organize the biannual international conference "Geometric Science of Information" (GSI).
Selected Publications
Matrix Information Geometry, F. Nielsen and R. Bhatia (Eds), ISBN 9783642302312, Springer (2013).
k-MLE: A fast algorithm for learning statistical mixture models, F. Nielsen, CoRR 1203.5181, IEEE ICASSP (2012).
Visual computing: Geometry, graphics, and vision, F. Nielsen, ISBN 9781584504276, Charles River Media (2005).
Worldviews
Keywords
News & Articles
Fast Proxy Centers for the Jeffreys Centroid: The Jeffreys–Fisher–Rao Center and the Gauss–Bregman Inductive Center
Approximation and bounding techniques for the Fisher-Rao distances
Beyond existing theories, into a new world ~the world of information geometry~
