Filters








8 Hits in 7.8 sec

Algorithms for Verifying Deep Neural Networks [article]

Changliu Liu, Tomer Arnon, Christopher Lazarus, Clark Barrett, Mykel J. Kochenderfer
2020 arXiv   pre-print
Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control.  ...  In addition, we provide pedagogical implementations of existing methods and compare them on a set of benchmark problems.  ...  The authors would like to thank many of the authors of the referenced papers for their help in clarifying their algorithms and reviewing early drafts of this survey: Weiming Xiang, Taylor Johnson, Hoang-Dung  ... 
arXiv:1903.06758v2 fatcat:25pqxtxpfzfz7phnnsx53q3j5y

Formal Certification Methods for Automated Vehicle Safety Assessment [article]

Tong Zhao, Ekim Yurtsever, Joel Paulson, Giorgio Rizzoni
2022 arXiv   pre-print
We also propose a unified scenario coverage framework that can provide either a formal or sample-based estimate of safety verification for full AVs.  ...  A majority of approaches used in providing safety guarantees for AV motion control originate from formal methods, especially reachability analysis (RA), which relies on mathematical models for the dynamic  ...  of deep neural network (DNN) controlled close-loop system [85] maxFRS of (possibly) occluded vehicle guarantees collision-free with possibly occluded vehicle(s) [86]  ... 
arXiv:2202.02818v2 fatcat:spgyrglbwjhshl2n43kyx722fa

[IEEE Robotics & Automation Society]

2012 IEEE robotics & automation magazine  
For the computation of reachable sets we use our method based on zonotopes as approximation sets.  ...  In this paper we investigate the effect of filtering on detection delay as an important alarm performance index. 11:30-11:50 WeA3.4 A Neural Network Approach to Damage Detection in Euler-Bernoulli  ... 
doi:10.1109/mra.2012.2229854 fatcat:rjrxtwk4jbcgjpvjdad6mougsq

IEEE Robotics & Automation Society

2012 IEEE robotics & automation magazine  
For the computation of reachable sets we use our method based on zonotopes as approximation sets.  ...  In this paper we investigate the effect of filtering on detection delay as an important alarm performance index. 11:30-11:50 WeA3.4 A Neural Network Approach to Damage Detection in Euler-Bernoulli  ... 
doi:10.1109/mra.2012.2230568 fatcat:33actbknxrel3jnag2kx7cncem

IEEE Robotics & Automation Society

2011 IEEE robotics & automation magazine  
For the computation of reachable sets we use our method based on zonotopes as approximation sets.  ...  In this paper we investigate the effect of filtering on detection delay as an important alarm performance index. 11:30-11:50 WeA3.4 A Neural Network Approach to Damage Detection in Euler-Bernoulli  ... 
doi:10.1109/mra.2011.941112 fatcat:owvu2behc5hulpcae2dp5myigm

IEEE Robotics & Automation Society

2011 IEEE robotics & automation magazine  
For the computation of reachable sets we use our method based on zonotopes as approximation sets.  ...  In this paper we investigate the effect of filtering on detection delay as an important alarm performance index. 11:30-11:50 WeA3.4 A Neural Network Approach to Damage Detection in Euler-Bernoulli  ... 
doi:10.1109/mra.2011.943480 fatcat:d2wvloyv6jcbzp2yathd52mx2u

Dagstuhl Reports, Volume 12, Issue 2, February 2022, Complete Issue [article]

2022
As a compromise between hand-designed and fully-learned audio representations, researchers have attempted to learn filters with constraints (e.g., phase invariance) or learn only parameters of pre-designed  ...  It was held in a hybrid format, with participants both in person and online.  ...  Further recent research directions include the design of network layers to mimic common front-end transforms or incorporate differentiable filter design methods into a neural network pipeline.  ... 
doi:10.4230/dagrep.12.2 fatcat:rf46qlh6fncxfgaoftoenmrmje

Connecting Performance Analysis and Visualization to Advance Extreme Scale Computing (Dagstuhl Seminar 14022) Randomized Timed and Hybrid Models for Critical Infrastructures (Dagstuhl Seminar 14031) Planning with Epistemic Goals (Dagstuhl Seminar 14032)

Frederik Armknecht, Helena Handschuh, Tetsu Iwata, Bart, Bernd Bremer, Valerio Mohr, Martin Pascucci, Schulz, Erika Ábrahám, Alberto Avritzer, Anne Remke, William Sanders (+13 others)
2014 unpublished
Pulina and A. Tacchella. An abstraction-refinement approach to verification of artificial neural networks. In Proc. of the 22nd Int.  ...  Neural Networks: The Official Journal of the International Neural Network Society, 2010. 20 M. Quigley, K. Conley, B. Gerkey, J. Faust, T. Foote, J. Leibs, R. Wheeler and A. Y. Ng.  ...  We introduce a simple distributed implementation of random linear network coding (RLNC) [8] and gives several scenarios arising in wireless network broadcast settings in which RLNC achieves large gains  ... 
fatcat:iqk466everfcdhf5guvz5ph2ee