Sciweavers

818 search results - page 128 / 164
» Regularized multi--task learning
Sort
View
3DPVT
2004
IEEE
131views Visualization» more  3DPVT 2004»
14 years 2 months ago
Neural Mesh Ensembles
This paper proposes the use of neural network ensembles to boost the performance of a neural network based surface reconstruction algorithm. Ensemble is a very popular and powerfu...
Ioannis P. Ivrissimtzis, Yunjin Lee, Seungyong Lee...
CORIA
2007
13 years 11 months ago
Apprentissage actif pour l'annotation de documents
ABSTRACT. In the framework of the LegDoc project at Xerox Research Centre Europe, we are developing components for the semantic annotation of semi-structured documents. While certa...
Loïc Lecerf, Boris Chidlovskii
ESANN
2001
13 years 11 months ago
Transfer functions: hidden possibilities for better neural networks
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
Wlodzislaw Duch, Norbert Jankowski
FLAIRS
2003
13 years 11 months ago
Optimizing F-Measure with Support Vector Machines
Support vector machines (SVMs) are regularly used for classification of unbalanced data by weighting more heavily the error contribution from the rare class. This heuristic techn...
David R. Musicant, Vipin Kumar, Aysel Ozgur
NIPS
2003
13 years 11 months ago
A Sampled Texture Prior for Image Super-Resolution
Super-resolution aims to produce a high-resolution image from a set of one or more low-resolution images by recovering or inventing plausible high-frequency image content. Typical...
Lyndsey C. Pickup, Stephen J. Roberts, Andrew Ziss...