2.7.   Neural Networks – Universal Calibration Tools

During the last decade, artificial neural networks have gained an increasing popularity in several fields of chemistry [46]-[49], whereby the variety of applications in chemistry is best illustrated in a book written by Zupan and Gasteiger [50]. In the field of multivariate calibration, the class of the multilayer feedforward backpropagation networks is most popular as they allow calibrating relationships, which are linear and nonlinear, and as no assumption of a specific type of model is needed [51]-[55]. In this section, the basics of the multilayer feedforward backpropagation neural networks are briefly explained and then the issues, which are of interest for this study, are introduced. A very detailed discussion of neural networks in multivariate calibration can be found in an excellent tutorial by Despagne and Massart [8]. More information about the mathematical background and about other neural network topologies can be found in textbooks [56]-[58].