The Faulty Behavior of Feedforward Neural Networks with Hard-Limiting Activation Function

Abstract

With the progress in hardware implementation of artificial neural networks, the ability to analyze their faulty behavior has become increasingly important to their diagnosis, repair, reconfiguration, and reliable application. The behavior of feedforward neural networks with hardlimiting activation function under stuck-at faults is studied in this article. It is shown that the stuck-at-M faults have a larger effect on the network's performance than the mixed stuck-at faults, which in turn have a larger effect than that of stuck-at-0 faults. Furthermore, the fault-tolerant ability of the network decreases with the increase of its size for the same percentage of faulty interconnections. The results of our analysis are validated by Monte-Carlo simulations.

Empirical Study of Least Sensitive FFANN for Weight-Stuck-at Zero Fault

“…Sensitivity analysis provides ability to analyze faulty behavior of neural hardware [3]. Error/fault in feedforward artificial neural network FFANN is classified as [20] Study of fault tolerance and robustness in neural networks needs following three areas to be explored [18]:…”