TIT
2008
14 years 2 months ago
2008
We prove the strongest known bound for the risk of hypotheses selected from the ensemble generated by running a learning algorithm incrementally on the training data. Our result i...
DBPL
1995
Springer
14 years 6 months ago
1995
Springer
We study the problem of maintaining recursively-de ned views, such as the transitive closure of a relation, in traditional relational languages that do not have recursion mechanis...
LICS
2009
IEEE
14 years 9 months ago
2009
IEEE
We provide in this article two characterisation results, describing exactly which terms verify the dinaturality diagram, in Church-style system F and in Curry-style system F. The ...