Empirical Study of FFANN Tolerance to Weight Stuck at Max/Min Fault

Fault tolerance property of artificial neural networks has been investigatedwith reference to the hardware model of artificial neural networks. Weightfault is an important link, which causes breakup between two nodes. In thispaper three types of weight faults have been explained. Experiments have beenperformed to demonstrate fault tolerance behavior of feedforward artificialneural network for weight-stuck-MAX/MIN fault. Effect of weight-stuck-MAX/MIN fault on trained network has been analyzed in this paper. Theobtained results suggest that networks are not fault tolerant to this type offault