Joint Optimization of Hidden Conditional Random Fields and Non Linear Feature Extraction

Abstract : We describe an hybrid model that combines deep neural networks (DNN) for nonlinear feature extraction and hidden conditional random fields (HCRF), i.e. conditional random fields with hidden states. The model is globally trained though joint optimization of HCRF and DNN parameters. To deal with this highly non convex optimization criterion, we propose a multi-step training which aims at providing a good initialization before the final joint optimization of all parameters. We investigate then the discriminative power of these models with respect to the architecture of the DNN, and compare our models to HMM and HCRF based algorithms on the IAM database.
Document type :
Conference papers
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-00706021
Contributor : Antoine Vinel <>
Submitted on : Friday, June 8, 2012 - 4:54:07 PM
Last modification on : Thursday, March 21, 2019 - 2:21:32 PM

Identifiers

Citation

Antoine Vinel, Trinh-Minh-Tri Do, Thierry Artières. Joint Optimization of Hidden Conditional Random Fields and Non Linear Feature Extraction. ICDAR 2011 - 11th International Conference on Document Analysis and Recognition, Sep 2011, Beijing, China. pp.513-517, ⟨10.1109/ICDAR.2011.109⟩. ⟨hal-00706021⟩

Share

Metrics

Record views

254