Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Kaniz Mishty"'
Publikováno v:
Information, Vol 14, Iss 9, p 516 (2023)
Universal adversarial perturbations are image-agnostic and model-independent noise that, when added to any image, can mislead the trained deep convolutional neural networks into the wrong prediction. Since these universal adversarial perturbations ca
Externí odkaz:
https://doaj.org/article/62973fb52f7d4e2cbcaf3b9664481488
Autor:
Kaniz Mishty, Mehdi Sadi
Publikováno v:
Proceedings of the Great Lakes Symposium on VLSI 2023.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b2117b78ed791784cb71f81ea926cd6
https://doi.org/10.1145/3583781.3590233
https://doi.org/10.1145/3583781.3590233
Autor:
Mehdi Sadi, Kaniz Mishty
We demonstrate the design of efficient and high-performance artificial intelligence (AI)/deep learning accelerators with customized spin transfer torque (STT)-MRAM (STT-MRAM) and a reconfigurable core. Based on model-driven detailed design space expl
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a68cee3a943e011a7a6818da7d13a24b
