Neural conditional random fields - Archive ouverte HAL Access content directly
Conference Papers Year :

Neural conditional random fields

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.
No file

Dates and versions

hal-01291978 , version 1 (22-03-2016)

Identifiers

  • HAL Id : hal-01291978 , version 1

Cite

Trinh Minh Tri Do, Thierry Artières. Neural conditional random fields. International Conference on Artificial Intelligence and Statistics (AISTAT), May 2010, Sardinia, Italy. pp.177-184. ⟨hal-01291978⟩
103 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More