187 search results - page 3 / 38 » Bounding the cost of learned rules |
ECML
2003
Springer
14 years 16 days ago
2003
Springer
Abstract. Classical learning algorithms from the fields of artificial neural networks and machine learning, typically, do not take any costs into account or allow only costs depe...
ALGORITHMICA
1998
13 years 7 months ago
1998
We consider the problem of dynamic reorganization of a linear list, where requests for the elements are generated randomly with fixed, unknown probabilities. The objective is to ...
SAT
2009
Springer
14 years 1 months ago
2009
Springer
Abstract. We offer a new understanding of some aspects of practical SAT-solvers that are based on DPLL with unit-clause propagation, clause-learning, and restarts. On the theoreti...
ALT
2008
Springer
14 years 4 months ago
2008
Springer
Abstract. We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the onl...
DATAMINE
2008
13 years 7 months ago
2008
Rules are commonly used for classification because they are modular, intelligible and easy to learn. Existing work in classification rule learning assumes the goal is to produce ca...