Title of article
Incremental neural networks for function approximation
Author/Authors
Chentouf، نويسنده , , R and Jutten، نويسنده , , C and Maignan، نويسنده , , M and Kanevsky، نويسنده , , M، نويسنده ,
Pages
3
From page
268
To page
270
Abstract
A new strategy for incremental building of multilayer feedforward neural networks is proposed in the context of approximation of functions from Rp to Rq using noisy data. A stopping criterion based on the properties of the noise is also proposed. Experimental results for both artificial and real data are performed and two alternatives of the proposed construction strategy are compared.
Keywords
function approximation , Adding neurons , Adding layers , model comparison , Stopping criterion
Journal title
Astroparticle Physics
Record number
2001259
Link To Document