A neural network with O(N) neurons for ranking N numbers in O(1/N) time

In this paper, we propose a neural network for ranking a given set of N numbers in O(1/N) time. The ordering of a set of numbers based on their relative magnitudes, which is analogous to sorting, is a fundamental operation in many algorithms. In comparison with other sorting networks reported in the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems. 1, Fundamental theory and applications Fundamental theory and applications, 2004-10, Vol.51 (10), p.2044-2051
Main Authors: Jayadeva, Rahman, S.A.
Format: Article
Language:English
Subjects:
Biology computing
Circuits
Computer networks
Convergence
Intelligent networks
Neural networks
Neurons
Operational amplifiers
Recurrent neural networks
Sorting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose a neural network for ranking a given set of N numbers in O(1/N) time. The ordering of a set of numbers based on their relative magnitudes, which is analogous to sorting, is a fundamental operation in many algorithms. In comparison with other sorting networks reported in the literature, the proposed network requires fewer neurons, and fewer interconnections between neurons. The interconnections use nonlinear synapses which are composed of comparators, and do not require any weighted interconnections between neurons, as used in conventional neural networks. The proposed network has many applications, including as a component of self-organizing feature maps and other systems where sorting is a frequent operation.
ISSN:1549-8328
1057-7122
1558-0806
DOI:10.1109/TCSI.2004.835665