Inductive Learning of Compact Rule Sets by Using Effcient Hypotheses Reduction

TitleInductive Learning of Compact Rule Sets by Using Effcient Hypotheses Reduction
Publication TypeTechnical Report
Year of Publication1992
AuthorsKoch, T.
Other Numbers774
Abstract

A method is described which reduces the hypotheses space with an efficient and easily interpretable reduction criteria called ? - reduction. A learning algorithm is described based on ? - reduction and analyzed by using probability approximate correct learning results. The results are obtained by reducing a rule set to an equivalent set of kDNF formulas.The goal of the learning algorithm is to induce a compact rule set describing the basic dependencies within a set of data. The reduction is based on criterion which is very flexible and gives a semantic interpretation of the rules which fulfill the criteria. Comparison with syntactical hypotheses reduction show that the ? - reduction improves search and has a smaller probability of missclassification.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1992/tr-92-069.pdf
Bibliographic Notes

ICSI Technical Report TR-92-069

Abbreviated Authors

T. Koch

ICSI Publication Type

Technical Report