A novel modification to backpropagation sample selection strategy


Redei, Laszlo and Wallinga, Hans (1997) A novel modification to backpropagation sample selection strategy. Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 389 (1-2). pp. 233-236. ISSN 0168-9002

open access
Abstract:Random sample selection method in backpropagation results in convergence on the error (root of mean squared error, RMSE) surface. These problems, which are caused by the extreme (worst-case) errors, can be solved by a different sample selection strategy. A sample selection strategy has been proposed, which provides lower maximal errors and a higher confidence level on the expense of slightly increased RMSE. Applications are presented in the field of spectroscopic ellipsometry (SE), a sensitive, non-destructive but indirect analytical technique. Demonstrative example shows feature common to simulated annealing in the sense of escaping local minima.
Item Type:Article
Copyright:© 1997 Elsevier Science
Research Group:
Link to this item:http://purl.utwente.nl/publications/15138
Official URL:https://doi.org/10.1016/S0168-9002(97)00135-6
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page

Metis ID: 112010