Comparing neural network approximations for different functional forms

Morgan, Peter Huw ORCID: https://orcid.org/0000-0002-8555-3493, Curry, Bruce and Beynon, Malcolm James ORCID: https://orcid.org/0000-0002-5757-270X 1999. Comparing neural network approximations for different functional forms. Expert Systems 16 (2) , pp. 60-71. 10.1111/1468-0394.00096

Full text not available from this repository.

Abstract

This paper examines the capacity of feedforward neural networks (NNs) to approximate certain functional forms. Its purpose is to show that the theoretical property of ‘universal approximation’, which provides the basic rationale behind the NN approach, should not be interpreted too literally. The most important issue considered involves the number of hidden layers in the network. We show that for a number of interesting functional forms better generalization is possible with more than one hidden layer, despite theoretical results to the contrary. Our experiments constitute a useful set of counter-examples.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Business (Including Economics)
Subjects:	H Social Sciences > H Social Sciences (General) Q Science > QA Mathematics
Uncontrolled Keywords:	mutlilayer perceptron; peak functions; generalization; universal approximation; hidden layers
Publisher:	Wiley-Blackwell
ISSN:	0266-4720
Last Modified:	21 Oct 2022 09:51
URI:	https://orca.cardiff.ac.uk/id/eprint/38031

Citation Data

Cited 9 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item