NEURAL NETWORKS WITH COUNTER-PROPAGATION LEARNING-STRATEGY USED FOR MODELING

The neural networks employing the counter-propagation learning strateg y are described and their use for making complex models and inverse mo dels is explained. Two examples show how such modelling strategy can y ield satisfactory results for the investigated systems. The first exam ple describes building a model for quantitative prediction of the so-c alled 'colour change' factor. The second example shows the generation of the forward and inverse model for the control of a chemical process in a non-isothermic continuously stirred tank reactor (CSTR).