Neural conditional random fields

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.

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Trinh Minh Tri Do, Thierry Artières
• Keywords: Deep Neural Networks, JMLR 2010, Non-linear Graphical Model, Scalable Probabilistic Model