Abstract
In this paper we consider in the developing conception of multi-valued neurons. First of all significant reinforcement of the learning algorithm which led to the 20–30 — times acceleration of the convergence of learning is proposed. Then neural network based on multi-valued neurons where each neuron is connected with restricted number of other ones (function of connections is defined as random function) is considered. Application of such an network to image recognition is proposed. Then approach to extrapolation of the temporal series based on the representation of the series as multiple-valued function, learning of the single neural element and furtheron forecasting of the function's values is also considered.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
