Premium
Rapid optimization and minimal complexity in computational neural network multivariate calibration of chlorinated hydrocarbons using Raman spectroscopy
Author(s) -
Egan William J.,
Angel S. Michael,
Morgan Stephen L.
Publication year - 2001
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/1099-128x(200101)15:1<29::aid-cem600>3.0.co;2-a
Subject(s) - artificial neural network , calibration , process (computing) , chemometrics , computation , computer science , raman spectroscopy , computational complexity theory , multivariate statistics , artificial intelligence , machine learning , biological system , algorithm , mathematics , statistics , physics , optics , biology , operating system
Improvements in the computational neural network modeling process are described with the goals of enhancing the optimization process and reducing NN model complexity. Improvements to the optimization process not only speed computation, but also can enhance the quality of the result. Complex NN models require more intensive optimization procedures and are considerably more difficult to interpret. Performance of these new algorithms is demonstrated by results from training neural networks to quantitate composition of mixtures of chlorinated hydrocarbons based on their Raman spectra. Copyright © 2000 John Wiley & Sons, Ltd.