… We simulate a memristive accelerator similar to [9], wherein each layer of selected neural network model is mapped to one or more 128×128 arrays and each memristive cell maintains …
T Liu, W Wen - 2019 IEEE/ACM International Conference on …, 2019 - ieeexplore.ieee.org
… far from scalable in the envisioned scenario of a neuralnetwork trained once in the cloud and … fault-tolerance of emerging neuralnetwork accelerators by leveraging the algorithmic error-…
… SNN faulttolerance by … neural hardware accelerator to efficiently support the proposed technique. The experimental results show that, for a 900-neuronnetwork with even a high fault …
… In this work, we explore applying redundancy only to the most critical elements within the NN hardware accelerator, opening a new design space exploration to reduce the resource …
… a different problem compared to our work; our goal is to enhance the faulttolerance of the given … ; only a few accelerators support this type of network architecture. Techniques have also …
… Abstract—Due to their growing popularity and computational cost, deep neuralnetworks (… This paper deals with the design of faulttolerant, systolic array based DNN accelerators for …
Y Zhang, S Lin, R Wang, Y Wang… - … , Automation & Test …, 2020 - ieeexplore.ieee.org
… This method, however, sacrifices the faulttolerance and … faulttolerance of SC, taking a ternary neuralnetwork (TNN) as an example, we propose a parallel SC-based NN accelerator …
H Guo, L Peng, J Zhang, Q Chen… - 2020 IEEE 38th …, 2020 - ieeexplore.ieee.org
… based neuralnetworks and propose a ReRAM-based accelerator with a dedicated pipeline design for Attention-based NeuralNetworks. When considering cells with hard faults in …
Z Gao, H Zhang, Y Yao, J Xiao, S Zeng… - … Transactions on Very …, 2022 - ieeexplore.ieee.org
… FaultTolerance for CNN Accelerators This section provides a survey of faulttolerance for CNN accelerators, and … of the neuralnetworks and introduce hardware or time redundancy for …