The use of cultural algorithms with evolutionary programming to guide decision tree induction in large databases

Author

Reynolds, Robert ; Al-Shehri, Hasan

Author_Institution

Dept. of Comput. Sci., Wayne State Univ., Detroit, MI, USA

fYear

1998

fDate

4-9 May 1998

Firstpage

541

Lastpage

546

Abstract

In this paper, we use an evolutionary computational approach based upon cultural algorithms to guide the incremental learning decision trees by ITI. The results are compared to those produced by ITI itself for a complex real-world database. The results suggest that ITI can indeed produce optimal trees in some cases, and can produce optimal trees using an evolutionary approach in others

Keywords

decision theory; divide and conquer methods; genetic algorithms; inference mechanisms; knowledge acquisition; learning (artificial intelligence); trees (mathematics); very large databases; complex real-world database; cultural algorithms; decision tree induction; evolutionary programming; incremental learning decision trees; large databases; Cultural differences; Data mining; Databases; Decision trees; Entropy; Genetic programming; Induction generators; Learning systems; Machine learning algorithms; Partitioning algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on

Conference_Location

Anchorage, AK

Print_ISBN

0-7803-4869-9

Type

conf

DOI

10.1109/ICEC.1998.700086

Filename

700086