Artificial neural networks (ANN) are used in various areas of science. But very often they demand considerable time expenses. Use of multiprocessing computers can become the decision of this problem. But nowadays realizations of ANN exist only for personal computers and there are no realizations for the super computer. Therefore the purpose of the given work is developing the parallel algorithms of ANN training.

Описана история открытия применения непрерывной логики для моделирования различных систем: динамика дискретных автоматов, динамическая диагностика цифровых устройств, синхронизация динамических систем, расчет систем обслуживания, дискретная оптимизации и др.