Empirical Study Of FFANNs Tolerance To Weight Stuck At Zero Fault
نویسندگان
چکیده
Fault tolerance property of artificial neural networks has been investigated with reference to the hardware model of artificial neural networks. Weight fault is an important link, which causes breakup between two nodes. In this paper weight fault has been explained. Experiments have been performed for Weight-stuck-0 fault. Effect of weight-stuck-0 fault on trained network has been analyzed in this paper. The obtained results suggest that networks are not fault tolerant to this type of fault. Keywordsartificial neural network,weight Fault, fault tolerance
منابع مشابه
Empirical Study of Least Sensitive FFANN for Weight-Stuck-at Zero Fault
An important consideration for neural hardware is its sensitivity to input and weight errors. In this paper, an empirical study is performed to analyze the sensitivity of feedforward neural networks for Gaussian noise to input and weight. 30 numbers of FFANN is taken for four different classification tasks. Least sensitive network for input and weight error is chosen for further study of fault ...
متن کاملA generalized ABFT technique using a fault tolerant neural network
In this paper we first show that standard BP algorithm cannot yeild to a uniform information distribution over the neural network architecture. A measure of sensitivity is defined to evaluate fault tolerance of neural network and then we show that the sensitivity of a link is closely related to the amount of information passes through it. Based on this assumption, we prove that the distribu...
متن کاملSchrödinger ’ s CRCs ( Fast
I revisit the fault-tolerance of cyclic redundancy checks (CRCs), expanding on the work of Driscoll et al [1]. I introduce the concepts of Schrödinger-Hamming weight and Schrödinger-Hamming distance, and I argue that under a fault model in which stuck-at-one-half or slightly-out-of-spec faults dominate, current methods for computing the fault detection of CRCs may be over-optimistic. Keywords-c...
متن کاملVLSI Realization of Artificial Neural Networks with Improved Fault Tolerance
The feed forward neural network which is a model of the cerebral neural network has in-built fault tolerance. The conventional back-propagation algorithm reduces errors between the learning examples and the output of a multilayer neural network (MNN). However, it is not assured that the MNN behaves in the same manner when faults occur. For these reasons the study of fault tolerance in artificia...
متن کاملDistributed fault tolerance in optimal interpolative nets
The recursive training algorithm for the optimal interpolative (OI) classification network is extended to include distributed fault tolerance. The conventional OI Net learning algorithm leads to network weights that are nonoptimally distributed (in the sense of fault tolerance). Fault tolerance is becoming an increasingly important factor in hardware implementations of neural networks. But faul...
متن کامل