973 citations · 1.1k across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2018★ 14 cited
Analyzing and Mitigating the Impact of Permanent Faults on a Systolic Array Based Neural Network Accelerator
Jeff Zhang, Tianyu Gu, Kanad Basu +1
Due to their growing popularity and computational cost, deep neural networks (DNNs) are being targeted for hardware acceleration. A popular architecture for DNN acceleration, adopt…
cs.LG2017★ 90 cited
SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud
Zahra Ghodsi, Tianyu Gu, Siddharth Garg
Inference using deep neural networks is often outsourced to the cloud since it is a computationally demanding task. However, this raises a fundamental issue of trust. How can a cli…