DYNAMIC BIOLOGICALLY-LIKE NEURAL NETWORKS IN TASKS OF ROBOTICS

DYNAMIC BIOLOGICALLY-LIKE NEURAL NETWORKS IN TASKS OF ROBOTICS

D.A. Trophimov
PhD, Federal state budgetary educational institution of higher professional education «Ufa State Aviation Technical University» (USATU), Senior Lecturer, K. Marx Str., 12, Ufa, The Republic of Bashkortostan, Russian Federation, tel.: +7(917)767-96-56, This email address is being protected from spambots. You need JavaScript enabled to view it. 

R.A. Munasypov
Doctor of Technical Science, USATU, Professor, K. Marx Str., 12, Ufa, The Republic of Bashkortostan, Russian Federation, tel.: +7(903)350-06-41, This email address is being protected from spambots. You need JavaScript enabled to view it. 


Abstract
Analysis of known information about biological neural networks' training is presented in the paper, and representation of training processes relating to artificial neural network is proposed. The mathematical description of the neuron model and learning rules is provided.

Key words
Neuron, neural networks, training process, mathematical model.

Year 2014 Issue number 4Consecutive issue number 5 Pages 10-12
UDC identifier: 573.6:007

 

Editorial office address: 21, Tikhoretsky pr., Saint-Petersburg, Russia, 194064, tel.: +7(812) 552-13-25 e-mail: zheleznyakov@rtc.ru