Sciweavers

667 search results - page 2 / 134
» Learning to Model Sequences Generated by Switching Distribut...
Sort
View
NN
2010
Springer
225views Neural Networks» more  NN 2010»
13 years 9 months ago
Learning to imitate stochastic time series in a compositional way by chaos
This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
Jun Namikawa, Jun Tani
KBSE
2000
IEEE
14 years 3 months ago
Systematic Generation of Dependable Change Coordination Plans for Automated Switching of Coordination Policies
Distributed information systems for decision support and e-commerce applications require coordination of multiple autonomous components and their services to accomplish a set of g...
Prasanta K. Bose, Mark G. Matthews
ICML
2006
IEEE
14 years 11 months ago
Combining discriminative features to infer complex trajectories
We propose a new model for the probabilistic estimation of continuous state variables from a sequence of observations, such as tracking the position of an object in video. This ma...
David A. Ross, Simon Osindero, Richard S. Zemel
ICML
2010
IEEE
13 years 11 months ago
High-Performance Semi-Supervised Learning using Discriminatively Constrained Generative Models
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
Gregory Druck, Andrew McCallum
EELC
2006
128views Languages» more  EELC 2006»
14 years 2 months ago
Evolving Distributed Representations for Language with Self-Organizing Maps
We present a neural-competitive learning model of language evolution in which several symbol sequences compete to signify a given propositional meaning. Both symbol sequences and p...
Simon D. Levy, Simon Kirby