2 code implementations • 16 Feb 2021 • Vasco Lopes, Saeid Alirezazadeh, Luís A. Alexandre
In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance.
Ranked #26 on Neural Architecture Search on NAS-Bench-201, CIFAR-100
no code implementations • 7 Dec 2020 • Saeid Alirezazadeh, Luís A. Alexandre
Load balancing allocation and scheduling ensures that the time between when the first node completes its scheduled tasks and when all other nodes complete their scheduled tasks is as short as possible.
Robotics
no code implementations • 2 Jul 2020 • Saeid Alirezazadeh, Khadijeh Alibabaei, Stephen P. Hubbell
For a rectangular sample area the species-area relationship follows the pattern, with some simplification, $S=c|A^{\beta}+a|^z$, where $S$ is the number of species in the area of size $A$ and $a, c, z$, and $\beta$ are constants with $z<1$ and $\beta\leq1$.
no code implementations • 1 Jul 2020 • Saeid Alirezazadeh, Khadijeh Alibabaei
The almost linear pattern of the log transformation of raw moments across scales allow us to extrapolate species abundance distribution for larger areas.