ÂÅÐÑÈß ÄËß ÑËÀÁÎÂÈÄßÙÈÕ
Enter
Login:
Password:
Forgot your password?
scientific activity
structureeducational projectsperiodicalsstaffpress centercontacts
ðóññêèé | english

Structural Models and Deep Learning

Joint IITP RAS, NRU HSE & Skoltech seminar  

March 1 (Wednesday), 1830, IITP, room 615  

Yuri Maximov (Skoltech, IITP RAS, Los Alamos National Laboratory)

TitleMulti-Class Classification: How to Deal with Multi-class Huge Scale Problems Efficiently?

AnnotationMulti-class classification problems are motivated by a numerous applications in nformational retrieval, text analysis and engineering systems. Nowadays problems require time and memory efficient algorithms with strong statistical  guarantees. In our talk we focus on a line of multi-class learning strategies proposed in a series of recent works joint with MR Amini, Z Harchaoui, F. Iutzeler,  B, Joshi, I Partalas and  D Reshetova. Finally we illustrate the efficiency of our algorithms on several practical problems arises in text analysis and energy systems.

27.02.2017 |
 

 

© Institute for Information Transmission Problems of the Russian Academy of Sciences (Kharkevich Institute), 2025
About  |  Contacts  |  Ïðîòèâîäåéñòâèå êîððóïöèè