N-bit Parity Neural Networks with minimum number of threshold neurons

2016

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.1515/eng-2016-0037
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

Abstract In this paper ordered neural networks for the Nbit parity function containing [log 2 (N + 1)] threshold elements are constructed. The minimality of this network is proved. The connection between minimum perceptrons of Gamb for the N-bit parity function and one combinatorial problems is established.