Graph Transformer Networks for Image Recognition

Abstract: This contribution takes the example of a check reading system to discuss the modeling and estimation issues associated with large scale pattern recognition systems.

Léon Bottou and Yann LeCun: Graph Transformer Networks for Image Recognition, Bulletin of the International Statistical Institute (ISI), 2005.

isi-2005.djvu isi-2005.pdf isi-2005.ps.gz

@article{bottou-lecun-2005,
  author = {Bottou, L\'{e}on and {LeCun}, Yann},
  title = {Graph Transformer Networks for Image Recognition},
  journal = {Bulletin of the International Statistical Institute (ISI)},
  year = {2005},
  note = {55th Session},
  url = {http://leon.bottou.org/papers/bottou-lecun-2005},
}

Notes

This short paper takes material from (Bottou et al., 1997) and (Lecun et al., 1998) and discusses the modular construction of large scale learning systems. It also shows the relation between this work and recent works on Conditional Random Fields [1].

  • [1] John Lafferty, Fernando Pereira, Andrew McCallum: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proceedings of the International Conference on Machine Learning (ICML'01), 2001.
papers/bottou-lecun-2005.txt · Last modified: 2006/08/09 12:47 by leonb
Driven by DokuWiki Recent changes RSS feed Valid CSS Valid XHTML 1.0