Sciweavers

4235 search results - page 302 / 847
» Process Spaces
Sort
View
NN
2008
Springer
146views Neural Networks» more  NN 2008»
15 years 3 months ago
Clustering and co-evolution to construct neural network ensembles: An experimental study
This paper introduces an approach called Clustering and Co-evolution to Construct Neural Network Ensembles (CONE). This approach creates neural network ensembles in an innovative ...
Fernanda L. Minku, Teresa Bernarda Ludermir
ICRA
2010
IEEE
143views Robotics» more  ICRA 2010»
15 years 2 months ago
Apprenticeship learning via soft local homomorphisms
Abstract— We consider the problem of apprenticeship learning when the expert’s demonstration covers only a small part of a large state space. Inverse Reinforcement Learning (IR...
Abdeslam Boularias, Brahim Chaib-draa
JAIR
2010
131views more  JAIR 2010»
15 years 2 months ago
Automatic Induction of Bellman-Error Features for Probabilistic Planning
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
Jia-Hong Wu, Robert Givan
MICAI
2010
Springer
15 years 2 months ago
Information Retrieval with a Simplified Conceptual Graph-Like Representation
We argue for that taking into account semantic relations between words in the text can improve information retrieval performance. We implemented the process of information retrieva...
Sonia Ordoñez-Salinas, Alexander F. Gelbukh
ICTAI
2010
IEEE
15 years 2 months ago
A Closer Look at MOMDPs
Abstract--The difficulties encountered in sequential decisionmaking problems under uncertainty are often linked to the large size of the state space. Exploiting the structure of th...
Mauricio Araya-López, Vincent Thomas, Olivi...