COMPLEXITY-BASED INDUCTION

Simple item page
dc.contributor.authorWitten, Ian H.eng
dc.contributor.authorConklin, Darrelleng
dc.date.accessioned2008-02-27T22:29:30Z
dc.date.available2008-02-27T22:29:30Z
dc.date.computerscience1999-05-27eng
dc.date.issued1991-07-01eng
dc.description.abstractA central problem in machine learning research is the evaluation of proposed theories from a hypothesis space. Without some sort of preference criterion, any two theories that "explain" a set of examples are equally acceptable. This paper presents \fIcomplexity-based induction\fR, a well-founded objective preference criterion. Complexity measures are described in two inductive inference settings: logical, where the observable statements entailed by a theory form a set; and probabilistic, where this set is governed by a probability distribution. With complexity-based induction, the goals of logical and probabilistic induction can be expressed identically--to extract maximal redundency from the world, in other words, to produce strings that are random. A major strength of the method is its application to domains where negative examples of concepts are scarce or an oracle unavailable. Examples of logic program induction are given to illustrate the technique.eng
dc.description.notesWe are currently acquiring citations for the work deposited into this collection. We recognize the distribution rights of this item may have been assigned to another entity, other than the author(s) of the work.If you can provide the citation for this work or you think you own the distribution rights to this work please contact the Institutional Repository Administrator at digitize@ucalgary.caeng
dc.identifier.department1991-439-23eng
dc.identifier.doihttp://dx.doi.org/10.11575/PRISM/31146
dc.identifier.urihttp://hdl.handle.net/1880/46187
dc.language.isoEngeng
dc.publisher.corporateUniversity of Calgaryeng
dc.publisher.facultyScienceeng
dc.subjectComputer Scienceeng
dc.titleCOMPLEXITY-BASED INDUCTIONeng
dc.typeunknown
thesis.degree.disciplineComputer Scienceeng
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1991-439-23.pdf
Size:
2.8 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.86 KB
Format:
Plain Text
Description:
Download
Collections
Science Research & Publications