Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/30973
Title: Minimal feedforward parity networks using threshold gates
Authors: Fung, HK
Li, LK
Issue Date: 2001
Publisher: M I T Press
Source: Neural computation, 2001, v. 13, no. 2, p. 319-326 How to cite?
Journal: Neural Computation 
Abstract: This article presents preliminary research on the general problem of reducing the number of neurons needed in a neural network so that the network can perform a specific recognition task. We consider a single-hidden-layer feedforward network in which only McCulloch-Pitts units are employed in the hidden layer. We show that if only interconnections between adjacent layers are allowed, the minimum size of the hidden layer required to solve the n-bit parity problem is n when n ≤ 4.
URI: http://hdl.handle.net/10397/30973
ISSN: 0899-7667
DOI: 10.1162/089976601300014556
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

7
Last Week
0
Last month
0
Citations as of Jan 14, 2017

WEB OF SCIENCETM
Citations

7
Last Week
0
Last month
0
Citations as of Jan 15, 2017

Page view(s)

17
Last Week
0
Last month
Checked on Jan 15, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.