Sigmoids distinguish more efficiently than heavisides

Authors:
Eduardo D. Sontag
Affiliations:
SYCONRutgers Center for Systems and Control, Department of Mathematics, Rutgers University, New Brunswick, NJ 08903 USA
Venue:
Neural Computation
Year:
1989

Citing 1
Cited 2

Multilayer feedforward networks are universal approximators

Neural Networks

Original Contribution: Training a 3-node neural network is NP-complete

Neural Networks
The use of random weights for the training of multilayer networks of neurons with Heaviside characteristics

Mathematical and Computer Modelling: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Every dichotomy on a 2k-point set in â聞聺N 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.