920 citations · 4.6k across the 68 of their papers we have counts for
69 papers
Efficient Model Adaptation for Continual Learning at the Edge
Zachary A. Daniels, Jun Hu, Michael Lomnitz +5
Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed o…
Learning with Local Gradients at the Edge
Michael Lomnitz, Zachary Daniels, David Zhang +1
To enable learning on edge devices with fast convergence and low memory, we present a novel backpropagation-free optimization algorithm dubbed Target Projection Stochastic Gradient…
Real-time Hyper-Dimensional Reconfiguration at the Edge using Hardware Accelerators
Indhumathi Kandaswamy, Saurabh Farkya, Zachary Daniels +8
In this paper we present Hyper-Dimensional Reconfigurable Analytics at the Tactical Edge (HyDRATE) using low-SWaP embedded hardware that can perform real-time reconfiguration at th…
A general approach to bridge the reality-gap
Michael Lomnitz, Zigfried Hampel-Arias, Nina Lopatina +1
Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect. A common approach to circumvent t…
The STAR Event Plane Detector
Joseph Adams, Annika Ewigleben, Sierra Garrett +15
The Event Plane Detector (EPD) is an upgrade detector to the STAR experiment at RHIC, designed to measure the pattern of forward-going charged particles emitted in a high-energy co…
Reducing audio membership inference attack accuracy to chance: 4 defenses
Michael Lomnitz, Nina Lopatina, Paul Gamble +4
It is critical to understand the privacy and robustness vulnerabilities of machine learning models, as their implementation expands in scope. In membership inference attacks, adver…