Analysis of Fault Tolerance in Artificial Neural Networks

68 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

When Neurons Fail (2017, background): “It is actually well known that the failure of neurons can be tolerated through additional learning phases [20], [21].”
On the Robustness of a Neural Network (2017, background): “To the best of our knowledge, the work on failures at the level of individual neurons has been mostly experimental [27], [28], [29], [30], [31], or, when it included a theoretical analysis, it focused on bounding the effect of the lost of a single neuron [32] or the cost in terms of additional learn”
Understanding Error Propagation in Deep Learning Neural Network (DNN) Accelerators and Applications (2017, background): “There were a few studies years ago on the fault tolerance of neural networks [1, 3, 44].”
MaxNVM: Maximizing DNN Storage Density and Inference Efficiency with Sparse Encoding and Error Mitigation (2019, result): “Abundant prior work exists related to the fault tolerance of DNNs [23, 25, 44, 44, 54, 57, 58, 65], and our presented fault tolerance studies (Section 4) confirm and expound upon previous results by additionally considering the resiliency of sparsely-encoded DNN weights.”
When Neurons Fail - Technical Report (2016, background): “In particular, in the case of multilayer (often called deep) neural networks, our results provide a guidance on how to distribute synaptic weights over layers, and how to tune the neuron activation function to increase robustness.”