Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Neural networks and finite-order approximations

Beynon, Malcolm James ORCID: https://orcid.org/0000-0002-5757-270X, Curry, Bruce and Morgan, Peter Huw ORCID: https://orcid.org/0000-0002-8555-3493 1999. Neural networks and finite-order approximations. IMA Journal of Management Mathematics 10 (3) , pp. 225-244. 10.1093/imaman/10.3.225

Full text not available from this repository.

Abstract

This paper investigates the approximation properties of standard feedforward neural networks (NNs) through the application of multivanate Thylor-series expansions. The capacity to approximate arbitrary functional forms is central to the NN philosophy, but is usually proved by allowing the number of hidden nodes to increase to infinity. The Thylor-series approach does not depend on such limiting cases, lie paper shows how the series approximation depends on individual network weights. The role of the bias term is taken as an example. We are also able to compare the sigmoid and hyperbolic-tangent activation functions, with particular emphasis on their impact on the bias term. The paper concludes by discussing the potential importance of our results for NN modelling: of particular importance is the training process.

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: Neural network; feedforward logistic networks; Thylor series; activation function; bias term
Publisher: Oxford University Press
ISSN: 1471-678X
Last Modified: 21 Oct 2022 09:51
URI: https://orca.cardiff.ac.uk/id/eprint/38032

Citation Data

Cited 6 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item