Sciweavers

4345 search results - page 447 / 869
» Relational Reinforcement Learning
Sort
View
ICML
2010
IEEE
15 years 8 months ago
Rectified Linear Units Improve Restricted Boltzmann Machines
Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all ...
Vinod Nair, Geoffrey E. Hinton
ML
2006
ACM
131views Machine Learning» more  ML 2006»
15 years 6 months ago
Markov logic networks
We propose a simple approach to combining first-order logic and probabilistic graphical models in a single representation. A Markov logic network (MLN) is a first-order knowledge b...
Matthew Richardson, Pedro Domingos
ML
2006
ACM
187views Machine Learning» more  ML 2006»
15 years 6 months ago
Modeling, analyzing, and synthesizing expressive piano performance with graphical models
Abstract Trained musicians intuitively produce expressive variations that add to their audience's enjoyment. However, there is little quantitative information about the kinds ...
Graham Grindlay, David P. Helmbold
NN
2006
Springer
120views Neural Networks» more  NN 2006»
15 years 6 months ago
Computational intelligence in earth sciences and environmental applications: Issues and challenges
This paper introduces a generic theoretical framework for predictive learning, and relates it to data-driven and learning applications in earth and environmental sciences. The iss...
Vladimir Cherkassky, Vladimir M. Krasnopolsky, Dim...
ML
2012
ACM
385views Machine Learning» more  ML 2012»
14 years 2 months ago
An alternative view of variational Bayes and asymptotic approximations of free energy
Bayesian learning, widely used in many applied data-modeling problems, is often accomplished with approximation schemes because it requires intractable computation of the posterio...
Kazuho Watanabe