×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • The neural networks recognition of the classes in real time

    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