| Home > Publications > Reports > Informatics (CW) |
CW 214
L. Dehaspe, L. De Raedt
DLAB - A declarative language bias for concept learning and knowledge discovery engines
Abstract
We describe the principles and functionalities of DLAB (Declarative LAnguage Bias), which is an algorithm for defining syntactically and traversing efficiently hypothesis spaces in the context of concept learning and knowledge discovery tasks. Though DLAB is designed for first-order languages it can also be used to constrain propositional concept spaces. In an appendix we document a DLAB Prolog library available via anonymous ftp.
report.pdf / mailto: L. Dehaspe