1 code implementation • 2 Feb 2023 • Hassan Dbouk, Naresh R. Shanbhag
In this work, we first demystify RECs as we derive fundamental results regarding their theoretical limits, necessary and sufficient conditions for them to be useful, and more.
1 code implementation • 14 Jun 2022 • Hassan Dbouk, Naresh R. Shanbhag
In this work we address this question both theoretically and empirically.
1 code implementation • NeurIPS 2021 • Hassan Dbouk, Naresh R. Shanbhag
But these methods are unable to improve throughput (frames-per-second) on real-life hardware while simultaneously preserving robustness to adversarial perturbations.
1 code implementation • NeurIPS 2021 • Ameya D. Patil, Michael Tuttle, Alexander G. Schwing, Naresh R. Shanbhag
Classical adversarial training (AT) frameworks are designed to achieve high adversarial accuracy against a single attack type, typically $\ell_\infty$ norm-bounded perturbations.
no code implementations • 25 Oct 2016 • Naresh R. Shanbhag
This position paper advocates a communications-inspired approach to the design of machine learning systems on energy-constrained embedded `always-on' platforms.