Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Yasser Shoukry"'
Autor:
Yasser Shoukry, Jaiprakash Pandey
Publisher's note: This edition from 2020 is based on AutoCAD 2021 and AutoCAD LT 2021 and does not make use of the most recent AutoCAD features. A new second edition, updated for AutoCAD 2023 and AutoCAD LT 2023 including new topics, such as Floating
Autor:
Xinfang Jin, Yasser Shoukry
Publikováno v:
ECS Transactions. 111:1159-1167
In this study, we simulated BZY electrolyte-supported proton-conducting solid oxide cell by coupling surface defect chemistry reaction with charged species transport. We validated the model parameters by concentration as a function of temperature, co
To mitigate the high energy demand of Neural Network (NN) based Autonomous Driving Systems (ADSs), we consider the problem of offloading NN controllers from the ADS to nearby edge-computing infrastructure, but in such a way that formal vehicle safety
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::337649cc4c75c6c85332339222b8e50d
http://arxiv.org/abs/2302.06572
http://arxiv.org/abs/2302.06572
Publikováno v:
25th ACM International Conference on Hybrid Systems: Computation and Control.
Autor:
Gil Lederman, Baihong Jin, Edward A. Lee, Matthew Weber, Yasser Shoukry, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia
Publikováno v:
ACM Transactions on Cyber-Physical Systems, vol 4, iss 4
Accurate localization from Cyber-Physical Systems (CPS) is a critical enabling technology for context-aware applications and control. As localization plays an increasingly safety-critical role, location systems must be able to identify and eliminate
In this paper, we present BERN-NN as an efficient tool to perform bound propagation of Neural Networks (NNs). Bound propagation is a critical step in wide range of NN model checkers and reachability analysis tools. Given a bounded input set, bound pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::932f0172559ec2ff5b58b807566367c3
Autor:
James Ferlez, Yasser Shoukry
In this paper, we consider the computational complexity of bounding the reachable set of a Linear Time-Invariant (LTI) system controlled by a Rectified Linear Unit (ReLU) Two-Level Lattice (TLL) Neural Network (NN) controller. In particular, we show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb9b2ca75873d82003d5d66057f79f89
Autor:
Ulices Santa Cruz, Yasser Shoukry
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031067723
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::834ad57148e489491a09af8ded6aba38
https://doi.org/10.1007/978-3-031-06773-0_11
https://doi.org/10.1007/978-3-031-06773-0_11
Autor:
James Ferlez, Yasser Shoukry
Publikováno v:
2021 60th IEEE Conference on Decision and Control (CDC).
In this paper, we consider the computational complexity of formally verifying the behavior of Rectified Linear Unit (ReLU) Neural Networks (NNs), where verification entails determining whether the NN satisfies convex polytopic specifications. Specifi
Publikováno v:
2021 60th IEEE Conference on Decision and Control (CDC).
While conventional reinforcement learning focuses on designing agents that can perform one task, meta-learning aims, instead, to solve the problem of designing agents that can generalize to different tasks (e.g., environments, obstacles, and goals) t