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

Neural Computation

Winter 1989, Vol. 1, No. 4, Pages 470-472
(doi: 10.1162/neco.1989.1.4.470)
© 1989 Massachusetts Institute of Technology
Sigmoids Distinguish More Efficiently Than Heavisides
Article PDF (126.84 KB)
Abstract

Every dichotomy on a 2k-point set in ℝN can be implemented by a neural net with a single hidden layer containing k sigmoidal neurons. If the neurons were of a hardlimiter (Heaviside) type, 2k − 1 would be in general needed.