Artificial neural networks （ANNs） are powerful compu- tational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance （FT）, an imp...Artificial neural networks （ANNs） are powerful compu- tational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance （FT）, an important property of ANNs, ensures their reliability when signifi- cant portions of a network are lost. In this paper, a fault/ noise injection-based （FIB） genetic algorithm （GA） is proposed to construct fault-tolerant ANNs. The FT per- formance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algo- rithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR （XOR） problem and the overlapping clas- sification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore Indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.展开更多
文摘Artificial neural networks （ANNs） are powerful compu- tational tools that are designed to replicate the human brain and adopted to solve a variety of problems in many different fields. Fault tolerance （FT）, an important property of ANNs, ensures their reliability when signifi- cant portions of a network are lost. In this paper, a fault/ noise injection-based （FIB） genetic algorithm （GA） is proposed to construct fault-tolerant ANNs. The FT per- formance of an FIB-GA was compared with that of a common genetic algorithm, the back-propagation algo- rithm, and the modification of weights algorithm. The FIB-GA showed a slower fitting speed when solving the exclusive OR （XOR） problem and the overlapping clas- sification problem, but it significantly reduced the errors in cases of single or multiple faults in ANN weights or nodes. Further analysis revealed that the fit weights showed no correlation with the fitting errors in the ANNs constructed with the FIB-GA, suggesting a relatively even distribution of the various fitting parameters. In contrast, the output weights in the training of ANNs implemented with the use the other three algorithms demonstrated a positive correlation with the errors. Our findings therefore Indicate that a combination of the fault/noise injection-based method and a GA is capable of introducing FT to ANNs and imply that the distributed ANNs demonstrate superior FT performance.
