Analysis of Fault Tolerance in Artificial Neural Networks

Piuri, Vincenzo

doi:10.1006/jpdc.2000.1663

Cited by 57 publications

(24 citation statements)

References 25 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Demonstration of non-fault-tolerance to specific faults [9] [14] asserts that the network can not be considered to be intrinsically fault tolerant. Edwards and Murray [15], use the regularization effect of weight noise to design a fault tolerant network.…”

Section: Related Workmentioning

confidence: 99%

“…The robustness of a backpropagation trained multilayer network to remove weights to/from the hidden layer and the influence of redundancy in the form of excess hidden neurons has been investigated in [14]. The effect of "Stuck-at-0" and "stuck-at-1" neurons on the solutions found in recurrent optimization networks is investigated in [26].…”

Section: Mse Mape and Other Global Measuresmentioning

confidence: 99%

See 1 more Smart Citation

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

Singh¹,

Shekhar²,

Chandra³

2010

IJAIA

View full text Add to dashboard Cite

Abstract-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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Mse Mape and Other Global Measuresmentioning

confidence: 99%

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

Singh¹,

Shekhar²,

Chandra³

2010

IJAIA

View full text Add to dashboard Cite

show abstract

“…There has been a substantial body of research into methods of introducing fault tolerance into neural networks (see [41] for an excellent review, as well as [36] or [40]). One approach to increasing a neural network's fault tolerance modifies the learning procedure to force a neuron to tolerate larger variations in the input signals.…”

Section: Neural Networkmentioning

confidence: 99%

“…On the other hand, since the computation is distributed, an error in one neuron or synapse potentially affects the whole network. It has been found that the degree of fault tolerance of a neural network is directly related to the degree of redundancy in the equilibrium solution to which it has been trained [41].…”

Section: Neural Networkmentioning

confidence: 99%

“…This level of redundancy may well be necessary, considering the expected high hardware defect rates at the nanometer scale. The second category includes techniques that are not included in the above more classical defect-or fault-tolerant techniques, such as the use of artificial neural networks for fault tolerance [41], and includes some techniques that are very specific to nano-scale devices.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Nanocomputing in the Presence of Defects and Faults: A Survey

Graham

Gokhale

Nano, Quantum and Molecular Computing

View full text Add to dashboard Cite

Computing systems implemented with nanotechnology will need to employ defect-and fault-tolerant measures to improve their reliability due to the large number of factors that may lead to imperfect device fabrication as well as the increased susceptibility to environmentally induced faults when using nanometerscale devices. Researchers have approached this problem of reliability from many angles and this survey will discuss many promising examples, ranging from classical fault-tolerant techniques to approaches specific to nanocomputing. The research results summarized here also suggest that many useful, yet strikingly different solutions may exist for tolerating defects and faults within nanocomputing systems. Also included in the survey are a number of software tools useful for quantifying the reliability of nanocomputing systems in the presence of defects and faults.

show abstract

Sensitivity Measurement of Neural Hardware: A Simulation Based Study

Singh

Chandra

2010

Communications in Computer and Information Science

View full text Add to dashboard Cite

Analysis of Fault Tolerance in Artificial Neural Networks

Cited by 57 publications

References 25 publications

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

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

Nanocomputing in the Presence of Defects and Faults: A Survey

Sensitivity Measurement of Neural Hardware: A Simulation Based Study

Contact Info

Product

Resources

About