Share Email Print

Proceedings Paper

Learnability of min-max pattern classifiers
Author(s): Ping-Fai Yang; Petros Maragos
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper introduces the class of thresholded min-max functions and studies their learning under the probably approximately correct (PAC) model introduced by Valiant. These functions can be used as pattern classifiers of both real-valued and binary-valued feature vectors. They are a lattice-theoretic generalization of Boolean functions and are also related to three-layer perceptrons and morphological signal operators. Several subclasses of the thresholded min- max functions are shown to be learnable under the PAC model.

Paper Details

Date Published: 1 November 1991
PDF: 15 pages
Proc. SPIE 1606, Visual Communications and Image Processing '91: Image Processing, (1 November 1991); doi: 10.1117/12.50358
Show Author Affiliations
Ping-Fai Yang, Harvard Univ. (United States)
Petros Maragos, Harvard Univ. (United States)

Published in SPIE Proceedings Vol. 1606:
Visual Communications and Image Processing '91: Image Processing
Kou-Hu Tzou; Toshio Koga, Editor(s)

© SPIE. Terms of Use
Back to Top