Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

February 2001, Vol. 13, No. 2, Pages 319-326
(doi: 10.1162/089976601300014556)
© 2001 Massachusetts Institute of Technology
Minimal Feedforward Parity Networks Using Threshold Gates
Article PDF (51.73 KB)
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.