[1]MA Shi-long,SUI Yue-fei,XU Ke.Limit behavior of prioritized inductive logic programs[J].CAAI Transactions on Intelligent Systems,2007,2(4):9-13.
Copy
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
2
Number of periods:
2007 4
Page number:
9-13
Column:
学术论文—人工智能基础
Public date:
2007-08-25
- Title:
-
Limit behavior of prioritized inductive logic programs
- Author(s):
-
MA Shi-long1; 2; SUI Yue-fei2; XU Ke1
-
1.School of Computer Science,Beihang University,Beijing 100083,China; 2.Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100080,China
-
- Keywords:
-
inductive logic program; machine learning; limit beha vior
- CLC:
-
TN911.7
- DOI:
-
-
- Abstract:
-
Limit behavior of inductive logic programs is an important research to pic, but it has not been deeply explored until now. When running incremental or online inductive learning algorithms on a computer, limit behavior should be tak en into account. An example is given to show that some inductive learning algori thms may produce errors in the long run if limit behavior is not considered. An inductive logic program is convergent if, given an increasing sequence of exampl e sets, the inductive logic program creates a corresponding sequence of Horn log ic programs which have the settheoretic limit. Furthermore, it is limitcorre ct if the limit of the sequence of the Horn logic programs is correct with respect to the limit of the sequence of the example sets. Two examples show that the GO LEM system is not limitcorrect. Finally, we propose an inductive logic program which is limitcorrect, called the prioritized GOLEM system. It i s proved that the prioritized GOLEM is limitcorrect under certain constraints.