PROCEEDINGS IPMU '08
Lazy Classification Algorithms Based on Deterministic and Inhibitory Rules
P. Delimata, M. Moshkov, A. Skowron, Z. Suraj.
In the paper, two families of lazy
classification algorithms of polynomial
time complexity are considered.
These algorithms are based on deterministic
(with a relation “attribute
= value” on the right hand side)
and inhibitory (with a relation “attribute
≠ value” on the right hand
side) rules, but the direct generation
of rules is not required. Instead
of this, the considered algorithms
extract efficiently for a new
object some information about the
set of rules which is next used by a
decision-making procedure. Results
of experiments show that the performance
of algorithms based on inhibitory
rules is in many cases better
than the performance of algorithms
based on deterministic rules.
 | PDF full paper |