no code implementations • 29 Dec 2022 • Akul Malhotra, Sumeet Kumar Gupta
Moreover, we show that SAQ-trained activation-sparse QDNNs show better accuracy in faulty settings than standard QDNNs trained conventionally.
no code implementations • 16 Sep 2022 • Karam Cho, Sumeet Kumar Gupta
Valley-spin hall (VSH) effect in monolayer WSe2 has been shown to exhibit highly beneficial features for nonvolatile memory (NVM) design.
no code implementations • 15 Sep 2019 • Shubham Jain, Sumeet Kumar Gupta, Anand Raghunathan
The use of lower precision has emerged as a popular technique to optimize the compute and storage requirements of complex Deep Neural Networks (DNNs).