The construction of minimal multilayered perceptrons: A case study for sorting

Zwieterinng, P.J, Aarts, E.H.L, & Wessels, J. (1993). The construction of minimal multilayered perceptrons: A case study for sorting. Neurocomputing 5 (4-5) 197-210. 10.1016/0925-2312(93)90007-P.

Full text not available from this repository.

Abstract

We consider the construction of minimal multilayered perceptrons for solving combinatorial optimization problems. Though general in nature, the proposed construction method is presented as a case study for the sorting problem. The presentation starts with an Full-size image (<1 K) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an Full-size image (<1 K) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm.

Item Type: Article
Uncontrolled Keywords: Minimal multilayered perceptrons; feed-forward neural networks; combinatorial optimization problems; sorting
Research Programs: Methodology of Decision Analysis (MDA)
Depositing User: Romeo Molina
Date Deposited: 18 Apr 2016 12:12
Last Modified: 27 Aug 2021 17:40
URI: https://pure.iiasa.ac.at/12764

Actions (login required)

View Item View Item