摘要：The application of artificial neural networks (ANNs) to mathematical modelling in mi-crobiology and biotechnology has been a promising and convenient tool for over 30 years becauseANNs make it possible to predict complex multiparametric dependencies. This article is devoted tothe investigation and justification of ANN choice for modelling the growth of a probiotic strain ofBifidobacterium adolescentis in a continuous monoculture, at low flow rates, under different oligofruc-tose (OF) concentrations, as a preliminary study for a predictive model of the behaviour of intestinalmicrobiota. We considered the possibility and effectiveness of various classes of ANN. Taking intoaccount the specifics of the experimental data, we proposed two-layer perceptrons as a mathematicalmodelling tool trained on the basis of the error backpropagation algorithm. We proposed and testedthe mechanisms for training, testing and tuning the perceptron on the basis of both the standard ratiobetween the training and test sample volumes and under the condition of limited training data, due tothe high cost, duration and the complexity of the experiments. We developed and tested the specificANN models (class, structure, training settings, weight coefficients) with new data. The validity ofthe model was confirmed using RMSE, which was from 4.24 to 980% for different concentrations.The results showed the high efficiency of ANNs in general and bilayer perceptrons in particular insolving modelling tasks in microbiology and biotechnology, making it possible to recommend thistool for further wider applications.
