Exact Classification with Two-Layered Perceptrons

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

[thumbnail of WP-92-049.pdf]

Download (842kB) | Preview


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: 27 Aug 2021 17:14
URI: https://pure.iiasa.ac.at/3649

Actions (login required)

View Item View Item