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.
|Journal||Nuclear instruments & methods in physics research. Section A : Accelerators, spectrometers, detectors and associated equipment|
|Publication status||Published - 1997|
|Event||New Computing Techniques in Physics Research V - AIHENP International Workshop 1996 - Lausanne, Switzerland|
Duration: 2 Sep 1996 → 6 Sep 1996
Conference number: 5