Sciweavers

908 search results - page 110 / 182
» Stochastic Finite Learning
Sort
View
ICANN
2010
Springer
13 years 10 months ago
Empirical Analysis of the Divergence of Gibbs Sampling Based Learning Algorithms for Restricted Boltzmann Machines
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
Asja Fischer, Christian Igel
ICML
2010
IEEE
13 years 10 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...
ML
2008
ACM
150views Machine Learning» more  ML 2008»
13 years 9 months ago
Learning probabilistic logic models from probabilistic examples
Abstract. We revisit an application developed originally using Inductive Logic Programming (ILP) by replacing the underlying Logic Program (LP) description with Stochastic Logic Pr...
Jianzhong Chen, Stephen Muggleton, José Car...
NC
2002
196views Neural Networks» more  NC 2002»
13 years 8 months ago
Beyond second-order statistics for learning: A pairwise interaction model for entropy estimation
Second order statistics have formed the basis of learning and adaptation due to its appeal and analytical simplicity. On the other hand, in many realistic engineering problems requ...
Deniz Erdogmus, José Carlos Príncipe...
ATAL
2008
Springer
13 years 11 months ago
Non-linear dynamics in multiagent reinforcement learning algorithms
Several multiagent reinforcement learning (MARL) algorithms have been proposed to optimize agents' decisions. Only a subset of these MARL algorithms both do not require agent...
Sherief Abdallah, Victor R. Lesser