Title: | MULTILAYER FEEDFORWARD NETWORKS WITH A NON-POLYNOMIAL ACTIVATION FUNCTION CAN APPROXIMATE ANY FUNCTION |
Authors: | Leshno, Moshe Lin, Valdimir Ya. Pinkus, Allan Schocken, Shimon |
Keywords: | Multilayer feedforward networks;Activation functions;role of threshold;Universal approximation capabilities;LP(μ) approximation |
Issue Date: | Mar-1992 |
Publisher: | Stern School of Business, New York University |
Series/Report no.: | IS-92-13 |
Abstract: | Several researchers characterized the activation function under which multilayer feedforward networks can act as universal approximators. We show that most of all the characterizations that were reported thus far in the literature are special cases of the following general result: a standard multilayer feedforward network with a locally bounded piecewise continuous activation function can approximate any continuous function to any degree of accuracy if and only if the network's activation function is not a polynomial. We also emphasize the important role of the threshold, asserting that without it the last theorem does not hold. |
URI: | http://hdl.handle.net/2451/14329 |
Appears in Collections: | IOMS: Information Systems Working Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
IS-92-13.pdf | 2.71 MB | Adobe PDF | View/Open |
Items in FDA are protected by copyright, with all rights reserved, unless otherwise indicated.