Studying the Possibilities and Efficiency of Operation with Signals in Neural Networks
- 作者: Khobotov A.G.1, Khil’ko A.I.1,2, Tel’nykh A.A.1
-
隶属关系:
- Institute of Applied Physics, Russian Academy of Sciences
- N. I. Lobachevsky State University of Nizhny Novgorod
- 期: 卷 61, 编号 1 (2018)
- 页面: 69-76
- 栏目: Article
- URL: https://journal-vniispk.ru/0033-8443/article/view/243862
- DOI: https://doi.org/10.1007/s11141-018-9871-x
- ID: 243862
如何引用文章
详细
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.
作者简介
A. Khobotov
Institute of Applied Physics, Russian Academy of Sciences
编辑信件的主要联系方式.
Email: algenn3@gmail.com
俄罗斯联邦, N. Novgorod
A. Khil’ko
Institute of Applied Physics, Russian Academy of Sciences; N. I. Lobachevsky State University of Nizhny Novgorod
Email: algenn3@gmail.com
俄罗斯联邦, N. Novgorod; Nizhny Novgorod
A. Tel’nykh
Institute of Applied Physics, Russian Academy of Sciences
Email: algenn3@gmail.com
俄罗斯联邦, N. Novgorod
补充文件
