Exact Classification with Two-Layered Perceptrons

Aarts EHL, Zwietering PJ, & Wessels J (1992). Exact Classification with Two-Layered Perceptrons. IIASA Working Paper. IIASA, Laxenburg, Austria: WP-92-049

[img]
Preview
Text
WP-92-049.pdf

Download (842kB) | Preview

Abstract

We study the capabilities of two-layered perceptrons for classifying exactly a given subset. Both necessary and sufficient conditions are derived for subsets to be exactly classifiable with two-layered perceptrons that use the hard-limiting response function. The necessary conditions can be viewed as generalizations of the linear-separability condition of one-layered perceptrons and confirm the conjecture that the capabilities of two-layered perceptrons are more limited than those of three-layered perceptrons. The sufficient conditions show that the capabilities of two-layered perceptrons extend beyond the exact classification of convex subsets. Furthermore, we present an algorithmic approach to the problem of verifying the sufficiency condition for a given subset.

Item Type: Monograph (IIASA Working Paper)
Research Programs: Methodology of Decision Analysis (MDA)
Depositing User: IIASA Import
Date Deposited: 15 Jan 2016 02:01
Last Modified: 24 Jul 2016 06:17
URI: http://pure.iiasa.ac.at/3649

Actions (login required)

View Item View Item

International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313