2317 search results - page 267 / 464 » classification 2008 |
144
click to vote
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
115
click to vote
SIAMSC
2008
15 years 3 months ago
2008
Abstract. We study high order numerical quadratures to one dimensional delta function integrals in this paper. This is motivated by the fact that traditional numerical quadratures ...
167
Voted
KDD
2008
ACM
16 years 4 months ago
2008
ACM
Many feature selection algorithms have been proposed in the past focusing on improving classification accuracy. In this work, we point out the importance of stable feature selecti...
115
click to vote
ICPR
2008
IEEE
16 years 5 months ago
2008
IEEE
The problem of character recognition in a book should be formulated significantly different from that of a single page or word. An ideal approach to design such a recognizer is to...
134
Voted
ECCV
2008
Springer
16 years 5 months ago
2008
Springer
The application of semi-supervised learning algorithms to large scale vision problems suffers from the bad scaling behavior of most methods. Based on the Expectation Regularization...