Title :
Quantitative determination of fault tolerance for neuronetwork devices of infocommunication systems
Author :
Galushkin, A.I. ; Danilin, S.N. ; Panteleev, S.V.
Author_Institution :
Int. Center of Inf. & Electron. “InterEVM”, Moscow, Russia
Abstract :
The option of quantitative criterion of level determination of fault tolerance of neural networks of any structure and appointment is developed. Fault tolerance of the neuronetwork device of recognition of a radio signal with QAM256 modulation is investigated. Dependence of determination result of fault tolerance level on the chosen indicator of quality of functioning of the neuronetwork device is studied.
Keywords :
fault tolerance; neural nets; quadrature amplitude modulation; signal processing; QAM256 modulation; fault tolerance level; infocommunication systems; neuronetwork devices; quantitative criterion; radio signal recognition; Artificial neural networks;
Conference_Titel :
Microwave & Telecommunication Technology (CriMiCo), 2014 24th International Crimean Conference
Conference_Location :
Sevastopol
Print_ISBN :
978-966-335-412-5
DOI :
10.1109/CRMICO.2014.6959416
