Neural network approach to numeric array sorting

2019

Closed access Metadata (CSL-JSON)
DOI 10.1117/12.2535916
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The functioning of a sorting network based on self-learning and self-setting of a ranks vector is considered. Sorting method by paired exchange is used with inserting of ranks vector as the elements weights vector of the input array, which allows considering an offered sorting network as a sorting neural network model.