FTSET-a software tool for fault tolerance evaluation and improvement

摘要: It is commonly assumed that neural networks have a built-in fault tolerance property mainly due to their parallel structure. The international community of discussed these properties until 1994 and afterward the subject has been mostly ignored. Recently, was again brought discussion possibility using in areas where graceful degradation would be an added value, like medical applications nano-electronics or space missions. Nevertheless, evaluation characteristics remained difficult because there were no systematic methods tools could easily applied given Artificial Neural Networks application. models first step for sorting ways developing capability building tool can evaluate improve this characteristic. present work proposes model, presents solutions improving it introduces Fault Tolerance Simulation Evaluation Tool evaluates improves tolerance.