1456 search results - page 248 / 292 » Two Techniques to Improve Finite Model Search |
ICCV
2009
IEEE
16 years 3 months ago
2009
IEEE
Graph-based semi-supervised learning has gained considerable
interests in the past several years thanks to its effectiveness
in combining labeled and unlabeled data through
labe...
89
Voted
PCM
2001
Springer
15 years 3 months ago
2001
Springer
This paper presents a fast and robust sprite generation algorithm for MPEG-4 video coding. Our contributions consist of two aspects. Firstly, a fast and robust Global Motion Estima...
104
Voted
ECML
2007
Springer
15 years 2 months ago
2007
Springer
Abstract. Ensemble methods are able to improve the predictive performance of many base classifiers. Up till now, they have been applied to classifiers that predict a single target ...
96
Voted
ATAL
2006
Springer
15 years 2 months ago
2006
Springer
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
ICONIP
2008
15 years 11 days ago
2008
Abstract. While injecting weight noise during training has been proposed for more than a decade to improve the convergence, generalization and fault tolerance of a neural network, ...