Neural conditional random fields

[edit]

Trinh–Minh–Tri Do, Thierry Artieres ;
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:177-184, 2010.

Abstract

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.

Related Material