DocumentCode :
3442386
Title :
Sensitivity to errors in artificial neural networks: a behavioral approach
Author :
Alippi, Cesare ; Piuri, Vincenzo ; Sami, Mariagiovanna
Author_Institution :
Dept. of Electron. & inf., Politecnico di Milano, Italy
Volume :
6
fYear :
1994
fDate :
30 May-2 Jun 1994
Firstpage :
459
Abstract :
A behavioral approach to the impact of errors due to faults in neural computation is analyzed. Starting from a geometrical description of errors affecting neural values, we derive the probability of error detection at the neuron´s output and at the network´s outputs
Keywords :
error analysis; error detection; neural nets; probability; ANN; artificial neural networks; behavioral approach; error detection probability; error sensitivity; neural computation faults; Artificial neural networks; Computer networks; Error analysis; Fault tolerance; Feedforward systems; Information analysis; Intelligent networks; Neural networks; Neurons; Solid modeling;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
Type :
conf
DOI :
10.1109/ISCAS.1994.409625
Filename :
409625
Link To Document :
بازگشت