Sciweavers

273 search results - page 32 / 55
» Learning the Structure of Deep Sparse Graphical Models
Sort
View
CVPR
2007
IEEE
14 years 10 months ago
Learning the Compositional Nature of Visual Objects
The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models tractable. Adopting this modeling ...
Björn Ommer, Joachim M. Buhmann
TOG
2012
255views Communications» more  TOG 2012»
11 years 11 months ago
A probabilistic model for component-based shape synthesis
We present an approach to synthesizing shapes from complex domains, by identifying new plausible combinations of components from existing shapes. Our primary contribution is a new...
Evangelos Kalogerakis, Siddhartha Chaudhuri, Daphn...
CORR
2010
Springer
167views Education» more  CORR 2010»
13 years 8 months ago
Network Flow Algorithms for Structured Sparsity
We consider a class of learning problems that involve a structured sparsityinducing norm defined as the sum of -norms over groups of variables. Whereas a lot of effort has been pu...
Julien Mairal, Rodolphe Jenatton, Guillaume Obozin...
TNN
1998
123views more  TNN 1998»
13 years 8 months ago
A general framework for adaptive processing of data structures
—A structured organization of information is typically required by symbolic processing. On the other hand, most connectionist models assume that data are organized according to r...
Paolo Frasconi, Marco Gori, Alessandro Sperduti
JMLR
2010
140views more  JMLR 2010»
13 years 3 months ago
Learning Non-Stationary Dynamic Bayesian Networks
Learning dynamic Bayesian network structures provides a principled mechanism for identifying conditional dependencies in time-series data. An important assumption of traditional D...
Joshua W. Robinson, Alexander J. Hartemink