Studying the Possibilities and Efficiency of Operation with Signals in Neural Networks
- Authors: Khobotov A.G.1, Khil’ko A.I.1,2, Tel’nykh A.A.1
- 
							Affiliations: 
							- Institute of Applied Physics, Russian Academy of Sciences
- N. I. Lobachevsky State University of Nizhny Novgorod
 
- Issue: Vol 61, No 1 (2018)
- Pages: 69-76
- Section: Article
- URL: https://journals.rcsi.science/0033-8443/article/view/243862
- DOI: https://doi.org/10.1007/s11141-018-9871-x
- ID: 243862
Cite item
Abstract
We discuss the possibility of recording and the efficiency of processing of information in freedynamics neural networks with context-dependent parameters when the data are presented in signal form. On the example of numerical stochastic experiments, we demonstrate the possibility of processing of information by free-dynamics neural networks. Closeness of the considered networks to structures of natural biological nature is discussed. Using particular examples, we study the stability of free-dynamics networks with context-dependent parameters in solving problems related to recording of signals in the presence of noise.
About the authors
A. G. Khobotov
Institute of Applied Physics, Russian Academy of Sciences
							Author for correspondence.
							Email: algenn3@gmail.com
				                					                																			                												                	Russian Federation, 							N. Novgorod						
A. I. Khil’ko
Institute of Applied Physics, Russian Academy of Sciences; N. I. Lobachevsky State University of Nizhny Novgorod
														Email: algenn3@gmail.com
				                					                																			                												                	Russian Federation, 							N. Novgorod; Nizhny Novgorod						
A. A. Tel’nykh
Institute of Applied Physics, Russian Academy of Sciences
														Email: algenn3@gmail.com
				                					                																			                												                	Russian Federation, 							N. Novgorod						
Supplementary files
 
				
			 
					 
						 
						 
						 
						 
				 
  
  
  
  
  Email this article
			Email this article  Open Access
		                                Open Access Access granted
						Access granted Subscription Access
		                                		                                        Subscription Access
		                                					