About Me
I
am currently a postdoctoral researcher at Università degli Studi di Milano, working under the supervision of Prof. Nicolò Cesa-Bianchi. My main research
areas are machine learning, computer
vision, and information theory.
My Research
My main interest has always been artificial
intelligence. I did my PhD at the University of Genova, mainly working
on biological inspired humanoid robotics. The emphasis of my work was
on computer vision, and in particual models of visual attention, and
machine learning. I have followed the framework of “development” as a
way to solve complex tasks, and at the same time to learn something
about human cognition from robotics.
After my PhD I decided to tackle the problem of artifical intelligence from a pure machine learning point of view. Hence my current research interests are theoretically motivated supervised and unsupervised learning algorithms. In particular I am interested in online learning methods for life-long learning, online active learning and kernel methods in general.
After my PhD I decided to tackle the problem of artifical intelligence from a pure machine learning point of view. Hence my current research interests are theoretically motivated supervised and unsupervised learning algorithms. In particular I am interested in online learning methods for life-long learning, online active learning and kernel methods in general.
News
- 11/6/10 DOGMA 0.20 released!
- 1/5/10 "OM-2: An Online Multi-class Multi-kernel Learning Algorithm" by Luo Jie, me, Marco Fornoni, Barbara Caputo, and Nicolò Cesa-Bianchi has been accepted as oral in the Online Learning for Computer Vision Workshop (in CVPR10)!
- 25/2/10 "Online-Batch Strongly Convex Multi Kernel Learning" by me, Luo Jie and Barbara Caputo has been accepted as oral in CVPR 2010!
- 25/2/10 "Safety in Numbers: Learning Categories from Few Examples with Multi Model
Knowledge Transfer" by Tatiana Tommasi, me, and Barbara Caputo has been accepted as poster in CVPR 2010!
Selected Publications
- F. Orabona, L. Jie, and B. Caputo. Online-Batch Strongly Convex Multi Kernel Learning. Accepted in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, June 2010 [PDF]
- F. Orabona, C. Castellini, B. Caputo, L. Jie, G. Sandini. On-line Independent Support Vector Machines. Pattern Recognition, 43(4), 1402-1412, 2010 [PDF] [CODE]
- F. Orabona, J. Keshet, and B. Caputo. Bounded Kernel-Based Online Learning. Journal of Machine Learning Research, 10(Nov):2643-2666, 2009 [PDF] [CODE]
- N. Cesa-Bianchi, C. Gentile and F. Orabona. Robust Bounds for Classification via Selective Sampling. In Proc. of the International Conference on Machine Learning (ICML), Montreal, Quebec, June 2009 [PDF] [TALK]
- F. Orabona,
G. Metta,
and G. Sandini. Object-based visual attention: a model for a behaving
robot. In Proc. of the 3rd International Workshop on Attention and
Performance in Computer Vision (WAPCV) (in CVPR05), Washington, DC,
USA, June 2005. IEEE Computer
Society ("Best paper" award) [PDF]
Me on the Italian Press
"E adesso Babybot, il robot che impara, aspetta un fratellino (più intelligente di lui)", Il Venerdì di Repubblica, 23 giugno 2006
"Che bella famiglia sono tutti baby robot", Il Secolo XIX - 30 luglio 2004
"Sfide finali per gli artisti del mattoncino", Corriere della Sera, 17 Giugno 1992
