Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function
26 Pages Posted: 23 Oct 2008
Date Written: March 1992
Abstract
Several researchers characterized the activation function under which multilayer feedforwardnetworks can act as universal approximators. We show that most of all the characterizationsthat were reported thus far in the literature are special cases of the followinggeneral result: a standard multilayer feedforward network with a locally bounded piecewisecontinuous activation function can approximate any continuous function to any degree ofaccuracy if and only if the network's activation function is not a polynomial. We alsoemphasize the important role of the threshold, asserting that without it the last theoremdoes not hold.
Keywords: Multilayer feedforward networks, Activation functions, role of threshold, Universal approximation capabilities, LP(μ) approximation
Suggested Citation: Suggested Citation
Do you have negative results from your research you’d like to share?
Recommended Papers
-
By Lennart F. Hoogerheide, Johan F. Kaashoek, ...
-
Simulation Based Bayesian Econometric Inference: Principles and Some Recent Computational Advances
By Lennart F. Hoogerheide, H. K. Van Dijk, ...
-
Bayesian Forecasting of Value at Risk and Expected Shortfall Using Adaptive Importance Sampling
-
AdMit: Adaptive Mixtures of Student-t Distributions
By David Ardia, Lennart F. Hoogerheide, ...
-
By David Ardia, Lennart F. Hoogerheide, ...
-
By Moshe Leshno and Shimon Schocken
-
By David Ardia, Lennart F. Hoogerheide, ...
-
On the Practice of Bayesian Inference in Basic Economic Time Series Models Using Gibbs Sampling
By Michiel De Pooter, Rene Segers, ...