The construction of minimal multi-layered perceptrons : a case study for sorting

P.J. Zwietering, E.H.L. Aarts, J. Wessels

Research output: Book/ReportBookScientific

Abstract

We consider the construction of minimal multi-layered perceptrons for solving combinatorial optimization problems. Though general in nature, the construction method is presented as a case study for the sorting problem. The presentation starts with an O((n!)^2) three-layered perceptron based on complete enumeration, that solves the sorting problem of n numbers. This network is then gradually reduced to an O(n^2) three-layered perceptron, which can be viewed as a neural implementation of Preparata's parallel enumerative sorting algorithm. Key words: minimal multi-layered percept1'Ons, feed-forward neural networks, combinatorial optimization problems, sorting.
Original languageEnglish
Place of PublicationEindhoven
PublisherTechnische Universiteit Eindhoven
Publication statusPublished - 1992
Externally publishedYes

Publication series

NameMemorandum COSOR

    Fingerprint

Cite this

Zwietering, P. J., Aarts, E. H. L., & Wessels, J. (1992). The construction of minimal multi-layered perceptrons : a case study for sorting. (Memorandum COSOR). Technische Universiteit Eindhoven.