• Information Technology
  • Human Resources
  • Careers
  • Giving
  • Library
  • Bookstore
  • Active Living
  • Continuing Education
  • Go Dinos
  • UCalgary Maps
  • UCalgary Directory
  • Academic Calendar
My UCalgary
Webmail
D2L
ARCHIBUS
IRISS
  • Faculty of Arts
  • Cumming School of Medicine
  • Faculty of Environmental Design
  • Faculty of Graduate Studies
  • Haskayne School of Business
  • Faculty of Kinesiology
  • Faculty of Law
  • Faculty of Nursing
  • Faculty of Nursing (Qatar)
  • Schulich School of Engineering
  • Faculty of Science
  • Faculty of Social Work
  • Faculty of Veterinary Medicine
  • Werklund School of Education
  • Information TechnologiesIT
  • Human ResourcesHR
  • Careers
  • Giving
  • Library
  • Bookstore
  • Active Living
  • Continuing Education
  • Go Dinos
  • UCalgary Maps
  • UCalgary Directory
  • Academic Calendar
  • Libraries and Cultural Resources
View Item 
  •   PRISM Home
  • Science
  • Science Research & Publications
  • View Item
  •   PRISM Home
  • Science
  • Science Research & Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

ON LEARNING DECISION TREES WITH LARGE OUTPUT DOMAINS

Thumbnail
Download
1995-567-19.pdf (253.8Kb)
1995-567-19.ps.gz (91.71Kb)
Download Record
Download to EndNote/RefMan (RIS)
Download to BibTex
Author
Bshouty, N.
Tamon, C.
Wilson, D.
Accessioned
2008-02-27T16:49:36Z
Available
2008-02-27T16:49:36Z
Computerscience
1999-05-27
Issued
1995-05-01
Subject
Computer Science
Type
unknown
Metadata
Show full item record

Abstract
For two disjoint sets of variables, X and Y, and a class of functions C, we define DT(X,Y,C) to be the class of all decision trees over X whose leaves are functions from C over Y. We study the learnability of DT(X,Y,C) using membership and equivalence queries. Boolean decision trees, DT(X,$empty$,{0,1}), were shown to be exactly learnable in [Bs93] but does this imply the learnability of decision trees that have non-boolean leaves? A simple encoding of all possible leaf values will work provided that the size of C is reasonable. Our investigation involves several cases where simple encoding is not feasible, i.e., when | C | is large. We show how to learn decision trees whose leaves are learnable concepts belonging to a class C, DT(X,Y,C), when the separation between the variables X and Y is known. A simple algorithm for decision trees whose leaves are constants, DT(X,$empty$,C), is also presented. Each case above requires at least s separate executions of the algorithm from [Bs93] where s is the number of distinct leaves of the tree but we show that if C is a bounded lattice, DT(X,$empty$,C) is learnable using only one execution of this algorithm.
Notes
We 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.ca
Corporate
University of Calgary
Faculty
Science
Doi
http://dx.doi.org/10.11575/PRISM/30482
Uri
http://hdl.handle.net/1880/45750
Collections
  • Science Research & Publications

Browse

All of PRISMCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

Download Results

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

  • Email
  • SMS
  • 403.220.8895
  • Live Chat

Energize: The Campaign for Eyes High

Privacy Policy
Website feedback

University of Calgary
2500 University Drive NW
Calgary, AB T2N 1N4
CANADA

Copyright © 2017