CONF Do_AISTATS_2010/IDIAP Neural conditional random fields Do, Trinh-Minh-Tri Artieres, Thierry EXTERNAL http://publications.idiap.ch/attachments/papers/2010/Do_AISTATS_2010.pdf PUBLIC Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics Chia Laguna, Sardinia, Italy 9 177-184 2010 JMLR: W&CP May 2010 We propose a non-linear graphical model for structured prediction. It combines the power of deep neural networks to extract high level features with the graphical framework of Markov networks, yielding a powerful and scalable probabilistic model that we apply to signal labeling tasks.