← Back to papers
2010 AISTATS AISTATS 2010

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.

🚀 Conference Pioneer — AISTATS 2010
🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning
🧭 Keyword Pioneer — neural conditional random field
🐣 Hot Topic Early Bird — deep neural network
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio

Authors

Trinh–Minh–Tri Do , Thierry Artières

Topics

Artificial Intelligence > Core AI > Causal Inference Deep Learning > Architectures > Neural Networks Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling Machine Learning > Core Methods > Graphical Models

Keywords

structured prediction graphical model deep neural network conditional random field markov network neural conditional random field high level feature neural network
Download PDF

Related papers

Towards Understanding Situated Natural Language 2010
Mass Fatality Incident Identification based on nuclear DNA evidence 2010
Locally Linear Denoising on Image Manifolds 2010
Negative Results for Active Learning with Convex Losses 2010
Collaborative Filtering on a Budget 2010