The work is devoted to the development of theoretical and practical basis for the use of intelligent technologies for productive extraction of knowledge from data sets for decision-making in real time.Developed the method construction of the accelerating algorithm, while controlling for allowable adequacy model allows training neural network models in the rate of real-time within a given risk. Proposed accelerating algorithm and neural network models are built based on a standard emulator, providing the required efficiency in the processing of the input array. within the limits.
Keywords: neyroemulyator speeding up the algorithm, cascade circuit training sample, gradient descent, back propagation of error