no code implementations • 11 Jan 2021 • Ariel Keller Rorabaugh, Silvina Caíno-Lores, Michael R. Wyatt II, Travis Johnston, Michela Taufer
To address this problem, we propose a performance estimation strategy that reduces the resources for training NNs and increases NAS throughput without jeopardizing accuracy.
no code implementations • 4 Feb 2020 • Mihaela Dimovska, Travis Johnston, Catherine D. Schuman, J. Parker Mitchell, Thomas E. Potok
In this work, we study Spiking Neural Networks in two neuromorphic architecture implementations with the goal of decreasing their size, while at the same time increasing their resiliency to hardware faults.