TASK PATTERN CHARACTERISTICS INFLUENCE ON THE HYPOTHESES ADEQUACY, GENERATED BY THE NEURAL NETWORK WITH THE CONNECTIONS BASED ON THE FOURIER-HOLOGRAPHY SCHEME

Z. Bekyasheva, V. N. Vasiliev, A. Vostrikov, A. V. Pavlov


Read the full article  ';

Abstract

Influence of task pattern on the inner representation size and its spectral characteristics on the hypotheses adequacy, generated by the neural network with the connections based on the Fourier-holography scheme is considered. It is shown that hypotheses adequacy increases with the growth of generalized pattern frequency.


Keywords: holography, neural network, artificial intelligence, cognitive system.

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Copyright 2001-2020 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика