Title :
Fault-tolerant analysis of feedback neural networks with threshold neurons
Author :
Zhang, Tao ; Hu, Dongcheng ; Yang, Shiyuan
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
In this paper, based on the statistical approach, the fault-tolerant behavior of feedback neural networks (FNN) with threshold neurons is discussed in detail. Firstly, the model of faults for FNN are defined. Secondly, the effect of link faults and error feedback on the fault-tolerant behavior are analyzed and corresponding formulas are given. Finally, the computer simulation shows the correctness of conclusions presented in this paper
Keywords :
digital simulation; fault tolerant computing; recurrent neural nets; statistical analysis; FNN; computer simulation; error feedback; fault-tolerant analysis; feedback neural networks; link faults; statistical approach; threshold neurons; Automation; Circuit faults; Fault tolerance; Fuzzy control; Hardware; Neural networks; Neurofeedback; Neurons; Output feedback; Statistical analysis;
Conference_Titel :
Test Symposium, 1999. (ATS '99) Proceedings. Eighth Asian
Conference_Location :
Shanghai
Print_ISBN :
0-7695-0315-2
DOI :
10.1109/ATS.1999.810752
