Incremental neural networks for function approximation
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.
- Publication:
-
Nuclear Instruments and Methods in Physics Research A
- Pub Date:
- February 1997
- DOI:
- 10.1016/S0168-9002(97)00081-8
- Bibcode:
- 1997NIMPA.389..268C