Tutorial review—Data processing by neural networks in quantitative chemical analysis
- 1 January 1993
- journal article
- review article
- Published by Royal Society of Chemistry (RSC) in The Analyst
- Vol. 118 (4) , 323-328
- https://doi.org/10.1039/an9931800323
Abstract
An overview is given of the current usage of artificial neural networks as mathematical models for non-linear calibration procedures. The emphasis is on practical aspects: the choice of the calibration samples, the required network characteristics for a given problem, various training methods and their efficiency and the validation of the network models. Some problems with the application of neural networks in multivariate calibration are considered, together with recent research aimed at solving these problems.Keywords
This publication has 19 references indexed in Scilit:
- Neural networks: A new method for solving chemical problems or just a passing phase?Published by Elsevier ,2002
- Wavelet transform for the evaluation of peak intensities in flow-injection analysisAnalytica Chimica Acta, 1992
- Artificial neural networks as a tool for soft-modelling in quantitative analytical chemistry: the prediction of the water content of cheeseAnalytica Chimica Acta, 1992
- Comparison of the training of neural networks for quantitative x-ray fluorescence spectrometry by a genetic algorithm and backward error propagationAnalytica Chimica Acta, 1991
- SuperSAB: Fast adaptive back propagation with good scaling propertiesNeural Networks, 1990
- Processing of signals from an ion-elective electrode array by a neural networkAnalytica Chimica Acta, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Increased rates of convergence through learning rate adaptationNeural Networks, 1988
- Parallel Distributed ProcessingPublished by MIT Press ,1986