Representativeness of learning samples for paradigm of variable-structure neural networks

The authors discuss the problem of the representativeness of a learning sample for the paradigm of the variable-structure neural network which synthesize neural networks for pattern recognition. They describe briefly the paradigm and classify recognition problems by the capability to simulate the learning sample. One problem involving a partially simulated learning sample is given as an example to demonstrate how the latter is created. Also presented are the learning sample simulation algorithm and experimental research that shows that the algorithm can be applied to other areas of recognition involving the partially simulated learning samples and to other paradigms