Sciweavers

984 search results - page 159 / 197
» ideas 2006
Sort
View
ICCV
2009
IEEE
13 years 5 months ago
Efficient multi-label ranking for multi-class learning: Application to object recognition
Multi-label learning is useful in visual object recognition when several objects are present in an image. Conventional approaches implement multi-label learning as a set of binary...
Serhat Selcuk Bucak, Pavan Kumar Mallapragada, Ron...
INTERSPEECH
2010
13 years 2 months ago
Prosodic speaker verification using subspace multinomial models with intersession compensation
We propose a novel approach to modeling prosodic features. Inspired by Joint Factor Analysis model (JFA), our model is based on the same idea of introducing subspace of model para...
Marcel Kockmann, Lukas Burget, Ondrej Glembek, Luc...
JMLR
2010
151views more  JMLR 2010»
13 years 2 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
CLEF
2006
Springer
13 years 11 months ago
QolA: Fostering Collaboration Within QA
In this paper we suggest a QA pilot task, dubbed QolA, whose joint rationale is allow for collaboration among systems, increase multilinguality and multicollection use, and investi...
Diana Santos, Luís Costa
JOCN
2010
96views more  JOCN 2010»
13 years 6 months ago
Medial Temporal Lobe Activity during Source Retrieval Reflects Information Type, not Memory Strength
■ The medial temporal lobes (MTLs) are critical for episodic memory but the functions of MTL subregions are controversial. According to memory strength theory, MTL subregions co...
Rachel A. Diana, Andrew P. Yonelinas, Charan Ranga...