DocumentCode
156163
Title
The method of tolerance increasing to internal and external noises for neural network devices
Author
Danilin, S.N. ; Makarov, M.V. ; Shchanikov, S.A.
Author_Institution
Murom Inst. Fed. State Budgetary Educ. Instn. of Higher Prof. Educ., Vladimir State Univ. named after Alexader Grigoryevich & Nickolay Grigoryevich Stoletovs, Vladimir, Russia
fYear
2014
fDate
7-13 Sept. 2014
Firstpage
320
Lastpage
321
Abstract
We propose a method to reduce the impacts of noise distorting the input data on accuracy (quality) of the neural networks´ operation. The essence of the method is to determine the necessary and sufficient digit capacity of input information and elements of neural networks. The offered method is realized in the form of the algorithm, whose work is shown by an example of some neural network devices.
Keywords
neural nets; noise; external noises; input information; internal noises; neural network devices; neural networks elements; Barium; Blogs; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Microwave & Telecommunication Technology (CriMiCo), 2014 24th International Crimean Conference
Conference_Location
Sevastopol
Print_ISBN
978-966-335-412-5
Type
conf
DOI
10.1109/CRMICO.2014.6959413
Filename
6959413
Link To Document