====== Graph Transformer Networks ====== 

{{talk-gtn.png?130 }}
This lecture describe Graph Transformer Networks 
It took place at the 2001 ICML workshop [[http://web.engr.oregonstate.edu/~tgd/ml2001-workshop|Machine Learning for Spatial and Temporal Data]] organized by [[http://web.engr.oregonstate.edu/~tgd|Tom Dietterich]].
[[:papers:bottou-97|Graph Transformer Networks]] are one of the most powerful and successful method for learning sequential data. About 10% to 20% of the checks written in the U.S. since 1996 have been processed by a Graph Transformer Network. 

Graph Transformer Networks are related to [[http://www.inference.phy.cam.ac.uk/hmw26/crf|Conditional Random Fields]] but have variable geometry and non-linear energies.

   * See [[http://leon.bottou.org/slides/gtn/bundled.djvu|the slides (djvu 234KB)]] [[http://leon.bottou.org/slides/gtn/gtn.pdf|(pdf 2.4MB)]].
   * See [[:papers:bottou-97|a short paper]] or [[:papers:lecun-98h|a long paper]].