no code implementations • 14 May 2022 • Wenzhe Guo, Mohammed E Fouda, Ahmed M. Eltawil, Khaled N. Salama
This work proposes a novel local training algorithm, BackLink, which introduces inter-module backward dependency and allows errors to flow between modules.
no code implementations • 13 Dec 2021 • Wenzhe Guo, Mohammed E. Fouda, Ahmed M. Eltawil, Khaled Nabil Salama
The results reveal that temporal truncation has a negative effect on the accuracy of classifying frame-based datasets, but leads to improvement in accuracy on dynamic-vision-sensor (DVS) recorded datasets.