Frank Nielsen

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).

>> Frank Nielsen Web Page

Computational Geometry / Information Geometry / Statistics / Machine Learning / Artificial Intelligence



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).


Frank Nielsen graduated the master in parallel computing from ENS (France), and obtained his PhD in computational geometry at INRIA (France).
He joined Sony CSL (Japan) in 1997 to first conduct research in visual computing and currently investigate the geometric sciences of information with path breaking applications ranging from data analytics to machine intelligence.
He wrote several textbooks and edited books, co-authored 220+ papers, and co-organize the international conference Geometric Science of Information (GSI).
He taught several computer science curricula at Ecole Polytechnique (France), and is a senior member of ACM and IEEE.