Sciweavers

52 search results - page 5 / 11
» ml 2002
Sort
View
ML
2002
ACM
100views Machine Learning» more  ML 2002»
13 years 10 months ago
Structure in the Space of Value Functions
Solving in an efficient manner many different optimal control tasks within the same underlying environment requires decomposing the environment into its computationally elemental ...
David J. Foster, Peter Dayan
ML
2002
ACM
107views Machine Learning» more  ML 2002»
13 years 10 months ago
Training Invariant Support Vector Machines
Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated...
Dennis DeCoste, Bernhard Schölkopf
ML
2002
ACM
121views Machine Learning» more  ML 2002»
13 years 10 months ago
Near-Optimal Reinforcement Learning in Polynomial Time
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
Michael J. Kearns, Satinder P. Singh
ENTCS
2002
95views more  ENTCS 2002»
13 years 10 months ago
A Proof Dedicated Meta-Language
We describe a proof dedicated meta-language, called Ltac, in the context of the Coq proof assistant. This new layer of meta-language is quite appropriate to write small and local ...
David Delahaye
CORR
2002
Springer
126views Education» more  CORR 2002»
13 years 10 months ago
Unsupervised Discovery of Morphemes
We present two methods for unsupervised segmentation of words into morphemelike units. The model utilized is especially suited for languages with a rich morphology, such as Finnis...
Mathias Creutz, Krista Lagus