Sigmoids Distinguish More Efficiently Than Heavisides
- 1 December 1989
- journal article
- Published by MIT Press in Neural Computation
- Vol. 1 (4) , 470-472
- https://doi.org/10.1162/neco.1989.1.4.470
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.Keywords
This publication has 0 references indexed in Scilit: