Neural conditional random fields

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v9-do10a, title = {Neural conditional random fields}, author = {Do, Trinh–Minh–Tri and Artieres, Thierry}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {177--184}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/do10a/do10a.pdf}, url = {https://proceedings.mlr.press/v9/do10a.html}, 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.} }
Endnote
%0 Conference Paper %T Neural conditional random fields %A Trinh–Minh–Tri Do %A Thierry Artieres %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-do10a %I PMLR %P 177--184 %U https://proceedings.mlr.press/v9/do10a.html %V 9 %X 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.
RIS
TY - CPAPER TI - Neural conditional random fields AU - Trinh–Minh–Tri Do AU - Thierry Artieres BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-do10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 177 EP - 184 L1 - http://proceedings.mlr.press/v9/do10a/do10a.pdf UR - https://proceedings.mlr.press/v9/do10a.html AB - 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. ER -
APA
Do, T. & Artieres, T.. (2010). Neural conditional random fields. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:177-184 Available from https://proceedings.mlr.press/v9/do10a.html.

Related Material