no code implementations • 18 Feb 2020 • Ashkan Yousefpour, Brian Q. Nguyen, Siddartha Devic, Guanhua Wang, Aboudy Kreidieh, Hans Lobel, Alexandre M. Bayen, Jason P. Jue
Nevertheless, when a neural network is partitioned and distributed among physical nodes, failure of physical nodes causes the failure of the neural units that are placed on those nodes, which results in a significant performance drop.
no code implementations • 3 Sep 2019 • Ashkan Yousefpour, Siddartha Devic, Brian Q. Nguyen, Aboudy Kreidieh, Alan Liao, Alexandre M. Bayen, Jason P. Jue
To articulate deepFogGuard, we introduce the elements and a model for the resiliency of distributed DNN inference.
16 code implementations • 16 Oct 2017 • Cathy Wu, Aboudy Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre M. Bayen
Furthermore, in single-lane traffic, a small neural network control law with only local observation is found to eliminate stop-and-go traffic - surpassing all known model-based controllers to achieve near-optimal performance - and generalize to out-of-distribution traffic densities.