[Lisa_seminaires] UdeM-McGill-MITACS machine learning seminar Fri Dec. 17 at 10h30, Z-209
Dumitru Erhan
dumitru.erhan at umontreal.ca
Mer 15 Déc 09:01:43 EST 2010
The UdeM-McGill-MITACS machine learning seminar series has its last Fall
seminar this* Friday. *Please note the changed location and time:
*
Label Embedding Trees for Large Multi-Class Tasks
*by Samy Bengio
Google Research
*Location*: Pavillon Claire-McNicoll (UdeM), room* Z-209*
*Time*: *Friday, December 17, 10:30 (!)*
*Abstract*: Multi-class classification becomes challenging at test time when
the number of classes is very large and testing against every possible class
can become computationally infeasible. This problem can be alleviated by
imposing (or learning) a structure over the set of classes. We propose an
algorithm for learning a tree-structure of classifiers which, by optimizing
the overall tree loss, provides superior accuracy to existing tree
labeling methods. We also propose a method that learns to embed labels in a
low dimensional space that is faster than non-embedding approaches and has
superior accuracy to existing embedding approaches.
Finally we combine the two ideas resulting in the {\em label embedding tree}
that outperforms alternative methods including One-vs-Rest while being
orders of magnitude faster.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://webmail.iro.umontreal.ca/mailman/private/lisa_seminaires/attachments/20101215/ccc635eb/attachment.html
Plus d'informations sur la liste de diffusion Lisa_seminaires