Sciweavers

Share
6 search results - page 1 / 2
» Modeling pixel means and covariances using factorized third-...
Sort
View
CVPR
2010
IEEE
11 years 8 months ago
Modeling pixel means and covariances using factorized third-order boltzmann machines
Learning a generative model of natural images is a useful way of extracting features that capture interesting regularities. Previous work on learning such models has focused on me...
Marc Aurelio Ranzato, Geoffrey E. Hinton
JMLR
2010
169views more  JMLR 2010»
11 years 3 months ago
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
Deep belief nets have been successful in modeling handwritten characters, but it has proved more difficult to apply them to real images. The problem lies in the restricted Boltzma...
Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E....
NECO
2010
136views more  NECO 2010»
11 years 6 months ago
Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
Roland Memisevic, Geoffrey E. Hinton
JMLR
2012
9 years 10 months ago
Multiple Texture Boltzmann Machines
We assess the generative power of the mPoTmodel of [10] with tiled-convolutional weight sharing as a model for visual textures by speci´Čücally training on this task, evaluating m...
Jyri J. Kivinen, Christopher K. I. Williams
ICASSP
2011
IEEE
10 years 12 months ago
Factored covariance modeling for text-independent speaker verification
Gaussian mixture models (GMMs) are commonly used to model the spectral distribution of speech signals for text-independent speaker verification. Mean vectors of the GMM, used in c...
Eryu Wang, Kong-Aik Lee, Bin Ma, Haizhou Li, Wu Gu...
books