Learning in the deepstructured conditional random fields (2009)
| Venue: | NIPS 2009 Workshop on Deep Learning for Speech Recognition and Related Applications |
| Citations: | 3 - 2 self |
BibTeX
@INPROCEEDINGS{Yu09learningin,
author = {Dong Yu and Li Deng and Shizhen Wang},
title = {Learning in the deepstructured conditional random fields},
booktitle = {NIPS 2009 Workshop on Deep Learning for Speech Recognition and Related Applications},
year = {2009}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We have proposed the deep-structured conditional random fields (CRFs) for sequential labeling and classification recently. The core of this model is its deep structure and its discriminative nature. This paper outlines the learning strategies and algorithms we have developed for the deep-structured CRFs, with a focus on the new strategy that combines the layer-wise unsupervised pre-training using entropy-based multi-objective optimization and the conditional likelihood-based back-propagation fine tuning, as inspired by the recent development in learning deep belief networks. 1
