Sciweavers

713 search results - page 6 / 143
» Evaluation of Different Approaches to Training a Genre Class...
Sort
View
ACL
2012
12 years 12 months ago
Fast and Robust Part-of-Speech Tagging Using Dynamic Model Selection
This paper presents a novel way of improving POS tagging on heterogeneous data. First, two separate models are trained (generalized and domain-specific) from the same data set by...
Jinho D. Choi, Martha Palmer
CVPR
2010
IEEE
15 years 4 months ago
Improving web-image search results using query-relative classifiers
Web image search using text queries has received considerable attention. However, current state-of-the-art approaches require training models for every new query, and are therefore...
Josip Krapac, Moray Allan, Jakob Verbeek, Frédér...
ICML
2008
IEEE
15 years 10 months ago
Classification using discriminative restricted Boltzmann machines
Recently, many applications for Restricted Boltzmann Machines (RBMs) have been developed for a large variety of learning problems. However, RBMs are usually used as feature extrac...
Hugo Larochelle, Yoshua Bengio
CVPR
2008
IEEE
15 years 11 months ago
Unifying discriminative visual codebook generation with classifier training for object category recognition
The idea of representing images using a bag of visual words is currently popular in object category recognition. Since this representation is typically constructed using unsupervi...
Liu Yang, Rong Jin, Rahul Sukthankar, Fréd&...
ESWA
2008
223views more  ESWA 2008»
14 years 9 months ago
Credit risk assessment with a multistage neural network ensemble learning approach
In this study, a multistage neural network ensemble learning model is proposed to evaluate credit risk at the measurement level. The proposed model consists of six stages. In the ...
Lean Yu, Shouyang Wang, Kin Keung Lai