Michael Everett

activity

20242026

most citedUncertainty-Aware Ankle Exoskeleton Control

1 citations · 2 across the 11 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

$(DNN)^{2}$ : Doubly Non-Negative Relaxations for Deep Neural Networks

Hanna Jiamei Zhang, Alan Papalia, Michael Everett +1

Existing linear program (LP) and semidefinite program (SDP) relaxations for rectified linear unit (ReLU) neural network (NN) verification yield overly-conservative safety guarantee…

cs.LG2025

Approximating Safety Feedback Without a Safety Oracle via Model Predictive Control

Jeff Pflueger, Michael Everett

Safe decision-making algorithms for control of mobile robots often require the existence of feedback to verify the safety of proposed actions. This feedback is assumed to be direct…

(DNN)2: Doubly Non-Negative Relaxations for Deep Neural Networks

Approximating Safety Feedback Without a Safety Oracle via Model Predictive Control

$(DNN)^{2}$ : Doubly Non-Negative Relaxations for Deep Neural Networks