Abstract
In this paper, we construct a mathematical artificial neural network architecture called the M-Hynuron (Multi-Hynuron) model, which is a hybrid architecture of connection and disconnection models. This M-Hynuron model is defined in a four-dimensional time-space, and consists of three U-Hynurons [artificial unit neuron model proposed by introducing magnetic field information into the conventional neuron model (McCulloch-Pitts' neuron model)]. These U-Hynurons are two connected and one unconnected U-Hynuron : N1, N2 and N3, and N1 and N2 which are connected as a network. The dynamics of this M-Hynuron model are analyzed mathematically. The analyses show that the function of information processing in the model is realized through the interaction among the U-Hynurons by both electric and magnetic information. Based on the mathematical analyses some computer simulations are carried out.
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 callMore From: TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
Disclaimer: 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.
