Sciweavers

3406 search results - page 427 / 682
» Computational models of classical conditioning
Sort
View
AAAI
1996
15 years 7 months ago
Learning to Take Actions
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Roni Khardon
BIOSYSTEMS
2008
84views more  BIOSYSTEMS 2008»
15 years 6 months ago
Decoding spike timing: The differential reverse-correlation method
It is widely acknowledged that detailed timing of action potentials is used to encode information, for example, in auditory pathways; however, the computational tools required to ...
Gasper Tkacik, Marcelo O. Magnasco
CN
2006
70views more  CN 2006»
15 years 6 months ago
Distribution of path durations in mobile ad-hoc networks - Palm's Theorem to the rescue
We first study the distribution of path duration in multi-hop wireless networks. We show that as the number of hops along a path increases, the path duration distribution can be a...
Yijie Han, Richard J. La, Armand M. Makowski, Seun...
ENTCS
2006
117views more  ENTCS 2006»
15 years 6 months ago
Interpreting SWRL Rules in RDF Graphs
An unresolved issue in SWRL (the Semantic Web Rule Language) is whether the intended semantics of its RDF representation can be described as an extension of the W3C RDF semantics....
Jing Mei, Harold Boley
NN
2002
Springer
224views Neural Networks» more  NN 2002»
15 years 6 months ago
Optimal design of regularization term and regularization parameter by subspace information criterion
The problem of designing the regularization term and regularization parameter for linear regression models is discussed. Previously, we derived an approximation to the generalizat...
Masashi Sugiyama, Hidemitsu Ogawa