Neural networks: a need for caution

Curry, Bruce and Morgan, Peter Huw ORCID: https://orcid.org/0000-0002-8555-3493 1997. Neural networks: a need for caution. Omega 25 (1) , pp. 123-133. 10.1016/S0305-0483(96)00052-7

Full text not available from this repository.

Abstract

This paper deals with the computational aspects of neural networks. Specifically, it is suggested that the now traditional method of backpropagation (BP) may not be the most appropriate basis for learning. The argument is based on the known deficiencies of gradient descent methods, of which BP is an application. Simulation results also suggest that improved performance may be obtained by employing direct optimization procedures such as the polytope algorithm. The main reason for such performance differences appears to be that the root mean square function is subject to narrow ‘valleys’ and other anomalies.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Business (Including Economics)
Subjects:	H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Uncontrolled Keywords:	neural network; backpropagation; polytope; gradient descent and direct optimization
Publisher:	Elsevier
ISSN:	0305-0483
Last Modified:	21 Oct 2022 09:49
URI:	https://orca.cardiff.ac.uk/id/eprint/37839

Citation Data

Cited 64 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item