Sciweavers

147 search results - page 7 / 30
» Discriminative Training of a Neural Network Statistical Pars...
Sort
View
CEC
2008
IEEE
13 years 9 months ago
Learning defect classifiers for visual inspection images by neuro-evolution using weakly labelled training data
This article presents results from experiments where a detector for defects in visual inspection images was learned from scratch by EANT2, a method for evolutionary reinforcement l...
Nils T. Siebel, Gerald Sommer
ICML
2008
IEEE
14 years 8 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
ISNN
2007
Springer
14 years 1 months ago
Discriminant Analysis with Label Constrained Graph Partition
In this paper, a space partition method called “Label Constrained Graph Partition” (LCGP) is presented to solve the Sample-InterweavingPhenomenon in the original space. We firs...
Peng Guan, Yaoliang Yu, Liming Zhang
SERA
2007
Springer
14 years 1 months ago
Comparative Analysis of Neural Network Techniques Vs Statistical Methods in Capacity Planning
Capacity planning is a technique which can be used to predict the computing resource needs of an organization for the future after studying current usage patterns. This is of spec...
Nalini Vasudevan, Gowri C. Parthasarathy
DAGSTUHL
2009
13 years 8 months ago
Statistical Mechanics of On-line Learning
We introduce and discuss the application of statistical physics concepts in the context of on-line machine learning processes. The consideration of typical properties of very large...
Michael Biehl, Nestor Caticha, Peter Riegler