- Research areas: Data science, Geometric science of information, Big Data, Machine Learning, High-dimensional statistics.

Challenge: Current Data Science is often biased by inappropriate representation, and adhoc data/model goodness-of-fit or distances (poster).

Goal: Learn appropriate data/model geometry for*Intrinsic Data Science*with principled distances.

How to: By building a theory of*Computational Information Geometry*...

... and showcase it in applications arising in data science, learning, intelligence, vision and imaging. [+]

[publications] (books | arxiv | DBLP) [lectures] [video] [slides] [software] [services/events/editorship][+] Recent highlights

- Teaching:

- Introduction to HPC with MPI for Data Science, ISBN 978-3-319-21902-8, Springer, 2016.
- A Concise and Practical Introduction to Programming Algorithms in Java, ISBN 978-1-84882-338-9, Springer, 2009. (also translated in Chinese)
- Visual Computing: Geometry, Graphics, and Vision, ISBN 1-58450-427-7, Charles River Media, 2005.
- Ecole Polytechnique: INF442, INF517, INF591, PSCs. (past teaching: INF311, INF555)

: Dual geometry of Shannon information

[+] Contact

© Frank Nielsen, September 2016. (old web page)