Sciweavers

2103 search results - page 33 / 421
» Approximate Learning of Dynamic Models
Sort
View
ICML
2010
IEEE
15 years 3 months ago
Learning Efficiently with Approximate Inference via Dual Losses
Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation...
Ofer Meshi, David Sontag, Tommi Jaakkola, Amir Glo...
ICML
2005
IEEE
16 years 2 months ago
Compact approximations to Bayesian predictive distributions
We provide a general framework for learning precise, compact, and fast representations of the Bayesian predictive distribution for a model. This framework is based on minimizing t...
Edward Snelson, Zoubin Ghahramani
ICML
2008
IEEE
16 years 2 months ago
Training restricted Boltzmann machines using approximations to the likelihood gradient
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Tijmen Tieleman
WAPCV
2007
Springer
15 years 8 months ago
Language Label Learning for Visual Concepts Discovered from Video Sequences
Computational models of grounded language learning have been based on the premise that words and concepts are learned simultaneously. Given the mounting cognitive evidence for conc...
Prithwijit Guha, Amitabha Mukerjee
WEBI
2009
Springer
15 years 8 months ago
Adapting Reinforcement Learning for Trust: Effective Modeling in Dynamic Environments
—In open multiagent systems, agents need to model their environments in order to identify trustworthy agents. Models of the environment should be accurate so that decisions about...
Özgür Kafali, Pinar Yolum