UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Maximum certainty approach to feedforward neural networks

Roberts, SJ; Penny, W; (1997) Maximum certainty approach to feedforward neural networks. Electronics Letters , 33 (4) pp. 306-307. 10.1049/el:19970211.

Full text not available from this repository.

Abstract

A Bayesian-based methodology is presented which leads to a data analysis system based around a committee of radial-basis function (RBF) networks. The authors show that this approach enables estimatation of the uncertainty associated with system outputs. Systems with differing numbers of internal degrees of freedom (weights) may hence be compared using training data only.

Type: Article
Title: Maximum certainty approach to feedforward neural networks
DOI: 10.1049/el:19970211
URI: http://discovery.ucl.ac.uk/id/eprint/1546010
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item