• 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.

DYNAMIC BIAS IS NECESSARY IN REAL WORLD

Thumbnail
Download
1991-428-12.pdf (1.868Mb)
Download Record
Download to EndNote/RefMan (RIS)
Download to BibTex
Author
Heise, Rosanna
MacDonald, Bruce A.
Accessioned
2008-02-26T22:38:30Z
Available
2008-02-26T22:38:30Z
Computerscience
1999-05-27
Issued
1991-04-01
Subject
Computer Science
Type
unknown
Metadata
Show full item record

Abstract
This paper discusses the bias present in machine learning systems, emphasizing its effect on learnability and complexity. A good bias must allow more concepts to be learned and/or decrease the complexity associated with learning. The paper develops an exhaustive framework for bias, with two important distinctions: \fIstatic\fR versus \fIdynamic\fR and \fIfocus\fR versus \fImagnify\fR. The well-known candidate elimination algorithm (Mitchell) is used to illustrate the framework. Real world learners need dynamic bias. The paper examines two representative systems. \s+2S\s-2TABB (Utgoff) dynamically magnifies the description space where learning would otherwise be impossible. \s+2E\s-2TAR is a prototype for learning robot assembly tasks from examples--a dynamic focusing mechanism reduces both the real world description space and the task construction complexity. Inductive learning must be viewed as a problem of dynamic search control.
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/30888
Uri
http://hdl.handle.net/1880/45580
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