Measuring the generalization capabilities of arbitrary classifiers

Mark E. Oxley; Amy L. Magnus

doi:10.1117/12.487484

4 August 2003 Measuring the generalization capabilities of arbitrary classifiers

Mark E. Oxley; Amy L. Magnus

Author Affiliations +

Proceedings Volume 5103, Intelligent Computing: Theory and Applications; (2003) https://doi.org/10.1117/12.487484
Event: AeroSense 2003, 2003, Orlando, Florida, United States

Abstract

Given a classifier trained on two-class data one wishes to determine how well the classifier will perform on new, unseen data. To do this task one typically uses the data to estimate a distribution of the data, generate new data from this distribution, and then test the data. Also, hold-out methods are used including cross-validation. We propose a new method that uses computational geometry techniques that produces a partial ordering on subsets in feature space and measures how well the classifier will perform on these subsets. There are some conditions on the classifier that must be satisfied in order that this measure, in fact, exists. We give the details for these conditions as well as the results concerning this special collection of classifiers. We derive the measure that quantifies the generalization capability for the special collection classifier.

Citation Download Citation

Mark E. Oxley, Mark E. Oxley, Amy L. Magnus, Amy L. Magnus, } "Measuring the generalization capabilities of arbitrary classifiers", Proc. SPIE 5103, Intelligent Computing: Theory and Applications, (4 August 2003); doi: 10.1117/12.487484; https://doi.org/10.1117/12.487484

ACCESS THE FULL ARTICLE

PERSONAL SIGN IN
Full access may be available with your subscription

Email or Username Forgot your username?

Password Forgot your password?

Show

Remember Email/Username on this computer

Remember Password

No SPIE account? Create an account
or Institutional Sign In via Shibboleth

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $14.40

Non-members: $18.00 ADD TO CART

Show All Keywords

Keywords/Phrases

Search In:

Publication Years